Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 31324
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Herz
    -0.06
     Patel
    -0.06
     forfe
    -0.06
     공동
    -0.06
     tedious
    -0.06
     REPLACE
    -0.06
     стати
    -0.06
     spéc
    -0.06
    manual
    -0.06
    Browsable
    -0.06
    POSITIVE LOGITS
     Vik
    0.07
     or
    0.06
     tah
    0.06
     fisheries
    0.06
     Relevant
    0.06
    userID
    0.06
    add
    0.06
    ITUDE
    0.06
     shell
    0.06
    itta
    0.06
    Activations Density 0.002%

    No Known Activations