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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9077
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash

    language related to technology and innovation.

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

    This neuron activates on emoji or other non-standard Unicode symbol tokens.

    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
     syndrome
    -0.07
     Syndrome
    -0.07
    _ME
    -0.07
     spectrum
    -0.07
    26
    -0.07
    膜
    -0.07
    飯
    -0.06
     Went
    -0.06
    28
    -0.06
     Tunisia
    -0.06
    POSITIVE LOGITS
    :'.$
    0.08
    _Callback
    0.07
    ffc
    0.06
     prac
    0.06
    175
    0.06
     �
    0.06
    "$
    0.06
    _SM
    0.06
    <c
    0.06
    getDrawable
    0.06
    Activations Density 0.004%

    No Known Activations