© 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. 3-RESID-POST-AA
    6. 95250
    Prev
    Next
    INDEX
    Explanations

    marathons

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �от
    -0.07
    .out
    -0.07
    oha
    -0.07
     cucumber
    -0.06
     reinc
    -0.06
     искус
    -0.06
    tuple
    -0.06
    وش
    -0.06
     Maximum
    -0.06
    .substring
    -0.06
    POSITIVE LOGITS
    .FromResult
    0.08
     drug
    0.07
    DoubleClick
    0.07
     backlash
    0.06
    acco
    0.06
    مع
    0.06
    bins
    0.06
    ズ
    0.06
    dcc
    0.06
    schools
    0.06
    Activations Density 0.098%

    No Known Activations