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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7949
    Prev
    Next
    INDEX
    Explanations

    Electronic devices

    np_max-act · gemini-2.0-flash

    The neuron fires on technical jargon—especially multimedia and communication hardware terms (e.g. audio, video, digital, camera, high-frequency) common in patent descriptions.

    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
    =file
    -0.06
    /tr
    -0.06
    imos
    -0.06
    Howard
    -0.06
    Arduino
    -0.06
    地区
    -0.06
     کردن
    -0.06
    	list
    -0.06
     intimidation
    -0.06
    _embeddings
    -0.06
    POSITIVE LOGITS
     стат
    0.07
     ketogenic
    0.07
     mutated
    0.07
     Sender
    0.06
     Soda
    0.06
     MQ
    0.06
    .accessToken
    0.06
     fatty
    0.06
    _PLATFORM
    0.06
     cree
    0.06
    Activations Density 0.050%

    No Known Activations