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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 53547
    Prev
    Next
    INDEX
    Explanations

    void

    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
     eviction
    -0.07
    (Get
    -0.06
    Cisco
    -0.06
     yönetic
    -0.06
     surroundings
    -0.06
    abilece
    -0.06
    BigDecimal
    -0.06
     disb
    -0.06
     paycheck
    -0.06
    _rate
    -0.06
    POSITIVE LOGITS
    LogLevel
    0.08
     AO
    0.07
    �프
    0.06
    iko
    0.06
    .getSharedPreferences
    0.06
    }')↵
    0.06
    getHeight
    0.06
    šní
    0.06
    (newState
    0.06
    iao
    0.06
    Activations Density 0.004%

    No Known Activations