© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 68971
    Prev
    Next
    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash

    mentions of collecting, gathering, or storing user data (i.e., references to data collection or reporting).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simil
    -0.07
    ($.
    -0.06
    620
    -0.06
     amen
    -0.06
    330
    -0.06
    ())),
    -0.06
    ImageData
    -0.06
    Fake
    -0.06
    む
    -0.06
     diver
    -0.06
    POSITIVE LOGITS
     scandal
    0.07
    .setRequestHeader
    0.06
    .Other
    0.06
    apollo
    0.06
     effortlessly
    0.06
     sodium
    0.06
    \Redirect
    0.06
     Monthly
    0.06
     Justice
    0.06
    (HttpServletRequest
    0.06
    Activations Density 0.000%

    No Known Activations