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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 28947
    Prev
    Next
    INDEX
    Explanations

    .

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expelled
    -0.08
     calcular
    -0.07
     GPS
    -0.06
    (Op
    -0.06
    一度
    -0.06
     stk
    -0.06
    pherical
    -0.06
    跡
    -0.06
    あり
    -0.06
    (SP
    -0.06
    POSITIVE LOGITS
    -del
    0.06
     franc
    0.06
    ámara
    0.06
     kann
    0.06
     uniformly
    0.06
    _NONE
    0.06
     Nine
    0.06
     Hizmet
    0.06
     Т
    0.06
    laş
    0.06
    Activations Density 0.009%

    No Known Activations