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. 11-RESID-POST-AA
    6. 53791
    Prev
    Next
    INDEX
    Explanations

    to

    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
     and
    -0.09
    тик
    -0.07
    fdb
    -0.07
     or
    -0.06
    ��
    -0.06
     Ga
    -0.06
     parked
    -0.06
     plan
    -0.06
     سیم
    -0.06
     dirs
    -0.06
    POSITIVE LOGITS
    —from
    0.08
    —including
    0.07
    -by
    0.07
    -of
    0.07
    ,to
    0.07
     включа
    0.07
    ,<
    0.06
    'ils
    0.06
     Reservation
    0.06
     ABOVE
    0.06
    Activations Density 0.285%

    No Known Activations