© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95379
    Prev
    Next
    INDEX
    Explanations

    oned

    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
    conv
    -0.07
    )*(
    -0.07
     obscure
    -0.07
     triangles
    -0.06
     tank
    -0.06
     tails
    -0.06
     Forces
    -0.06
     ".$
    -0.06
     Morph
    -0.06
    .wall
    -0.06
    POSITIVE LOGITS
     reck
    0.19
     reckon
    0.19
    oned
    0.10
    oning
    0.09
    ุปกรณ
    0.08
     QUEUE
    0.07
     справи
    0.07
     Radi
    0.07
    kening
    0.07
     baseman
    0.07
    Activations Density 0.002%

    No Known Activations