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. 7-RESID-POST-AA
    6. 111615
    Prev
    Next
    INDEX
    Explanations

    compartments

    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
    hi
    -0.08
    267
    -0.08
    oshi
    -0.08
    ui
    -0.08
     six
    -0.07
    972
    -0.07
    545
    -0.07
    005
    -0.07
    UI
    -0.07
     Rita
    -0.07
    POSITIVE LOGITS
     compartments
    0.18
     compartment
    0.18
     compart
    0.09
    artment
    0.08
     Spart
    0.07
     ngăn
    0.07
    .getOwnProperty
    0.07
     прием
    0.06
    मक
    0.06
     vlan
    0.06
    Activations Density 0.002%

    No Known Activations