© 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. 7-RESID-POST-AA
    6. 80437
    Prev
    Next
    INDEX
    Explanations

    remaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Mult
    -0.08
     invented
    -0.08
     اتحاد
    -0.07
     pública
    -0.07
    _SIGN
    -0.07
     falsely
    -0.07
     prefer
    -0.07
     Treat
    -0.07
     public
    -0.07
     scandal
    -0.07
    POSITIVE LOGITS
     remaining
    0.17
    remaining
    0.11
     Remaining
    0.10
    Remaining
    0.09
    _remaining
    0.07
    portun
    0.07
    .remaining
    0.06
    _remain
    0.06
    AREN
    0.06
    NAV
    0.06
    Activations Density 0.007%

    No Known Activations