© 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. 7-RESID-POST-AA
    11. 112205
    Prev
    Next
    INDEX
    Explanations

    line

    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
    Val
    -0.07
     Fare
    -0.07
    /proto
    -0.07
    олева
    -0.07
    defer
    -0.07
    كية
    -0.06
     معرف
    -0.06
    极
    -0.06
    کو
    -0.06
    utral
    -0.06
    POSITIVE LOGITS
     dobr
    0.06
    ACE
    0.06
    enen
    0.06
    .createStatement
    0.06
     dök
    0.06
     line
    0.06
    حت
    0.06
     LINE
    0.06
     incarceration
    0.06
     sqlCommand
    0.06
    Activations Density 0.009%

    No Known Activations