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. 83380
    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
    "L
    -0.08
    epochs
    -0.07
    олит
    -0.07
    不会
    -0.07
     srpna
    -0.07
     Osborne
    -0.07
    @
    -0.06
    اضر
    -0.06
     divorce
    -0.06
    "@
    -0.06
    POSITIVE LOGITS
    aurant
    0.06
     reconoc
    0.06
     Dimit
    0.06
    _ADD
    0.06
     意
    0.06
    -facebook
    0.06
     ve
    0.06
    ({↵↵
    0.06
    internet
    0.06
     iş
    0.06
    Activations Density 0.005%

    No Known Activations