© 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. 66149
    Prev
    Next
    INDEX
    Explanations

    order

    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
    faculty
    -0.06
    Dst
    -0.06
     ads
    -0.06
    cxx
    -0.06
     substring
    -0.06
    .dead
    -0.06
     MATLAB
    -0.06
     Jr
    -0.06
     Jean
    -0.06
    POSITIVE LOGITS
     пред
    0.07
     тому
    0.06
    τές
    0.06
     bif
    0.06
    (rand
    0.06
    _styles
    0.06
    προ
    0.06
    _ass
    0.06
    adaki
    0.06
    ักร
    0.06
    Activations Density 0.010%

    No Known Activations