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. 57371
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    την
    -0.07
     operative
    -0.06
    ın
    -0.06
     Eve
    -0.06
    вается
    -0.06
    тия
    -0.06
     japan
    -0.06
    teen
    -0.06
     الرو
    -0.06
    ském
    -0.05
    POSITIVE LOGITS
    oolStrip
    0.07
    masından
    0.07
     �
    0.06
    RIX
    0.06
    ARR
    0.06
    $link
    0.06
    dateFormat
    0.06
                                            ↵
    0.06
    asc
    0.06
     histograms
    0.06
    Activations Density 0.034%

    No Known Activations