© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 54496
    Prev
    Next
    INDEX
    Explanations

    Appear

    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
    .timeline
    -0.08
     Schumer
    -0.07
    (${
    -0.06
     sku
    -0.06
     будів
    -0.06
     ryb
    -0.06
    _SCOPE
    -0.06
    ायल
    -0.05
    ولد
    -0.05
    (mock
    -0.05
    POSITIVE LOGITS
    urrences
    0.07
     pepp
    0.07
    _stats
    0.06
    	exp
    0.06
    compute
    0.06
    _border
    0.06
    _backward
    0.06
     bravery
    0.06
     kdo
    0.06
     energetic
    0.06
    Activations Density 0.070%

    No Known Activations