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. 7-RESID-POST-AA
    6. 21450
    Prev
    Next
    INDEX
    Explanations

    Dates

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phase
    -0.07
    "<
    -0.07
     trách
    -0.07
    ــ
    -0.06
    [counter
    -0.06
     هزار
    -0.06
    した
    -0.06
     aus
    -0.06
    >d
    -0.06
     мар
    -0.06
    POSITIVE LOGITS
    $",
    0.06
     overridden
    0.06
    šil
    0.06
     zih
    0.05
    .pin
    0.05
    _None
    0.05
    efa
    0.05
    Resizable
    0.05
     UART
    0.05
    อน
    0.05
    Activations Density 0.044%

    No Known Activations