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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 54724
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    osc
    -0.08
     wanna
    -0.08
     Fore
    -0.07
    박
    -0.07
    杉
    -0.06
    .Remove
    -0.06
    anno
    -0.06
    Transactions
    -0.06
    _atts
    -0.06
    Dia
    -0.06
    POSITIVE LOGITS
    .setOn
    0.07
     compared
    0.07
    (params
    0.07
    το
    0.06
    ží
    0.06
    ('_
    0.06
    entina
    0.06
    .events
    0.06
    "--
    0.06
     minWidth
    0.06
    Activations Density 0.114%

    No Known Activations