© 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. 11-RESID-POST-AA
    6. 123928
    Prev
    Next
    INDEX
    Explanations

    of

    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_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
     ----
    -0.07
     деся
    -0.07
    soup
    -0.06
    าจ
    -0.06
    subst
    -0.06
    とな
    -0.06
    .DEBUG
    -0.06
     EVP
    -0.06
     것을
    -0.06
     talk
    -0.06
    POSITIVE LOGITS
    maf
    0.07
     Chin
    0.07
     LIFE
    0.06
     emotionally
    0.06
     voy
    0.06
     militants
    0.06
     Electronics
    0.06
     jour
    0.06
    gst
    0.06
    nite
    0.06
    Activations Density 0.001%

    No Known Activations