© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57701
    Prev
    Next
    INDEX
    Explanations

    computer problems

    np_max-act · gemini-2.0-flash

    issues related to system responsiveness during installations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on language describing technical failures or error conditions, such as crashes, freezes, and other malfunction symptoms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elephant
    -0.06
     scenario
    -0.06
     resilient
    -0.06
     lamp
    -0.06
    oldemort
    -0.06
     hạn
    -0.06
    _library
    -0.06
    .adapter
    -0.06
    кра
    -0.06
    だ
    -0.06
    POSITIVE LOGITS
     getS
    0.07
    ��
    0.07
    .getAttribute
    0.06
     Exclude
    0.06
     Rim
    0.06
     orig
    0.06
     Restart
    0.06
    قط
    0.06
    ragment
    0.06
     Archie
    0.06
    Activations Density 0.047%

    No Known Activations