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. 9920
    Prev
    Next
    INDEX
    Explanations

    medicine/biology

    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
     정책
    -0.07
    MASK
    -0.07
    >y
    -0.07
    ixmap
    -0.06
    ường
    -0.06
    _letters
    -0.06
    BX
    -0.06
    horse
    -0.06
    IW
    -0.06
    -house
    -0.06
    POSITIVE LOGITS
     PCA
    0.07
     Celtics
    0.06
    (constants
    0.06
     مى
    0.06
     signup
    0.06
     Medina
    0.06
    (HttpServletRequest
    0.06
     declare
    0.06
     lv
    0.06
     �
    0.06
    Activations Density 0.000%

    No Known Activations