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. 129739
    Prev
    Next
    INDEX
    Explanations

    website advertisements

    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
    .argsort
    -0.06
    ındaki
    -0.06
     psz
    -0.06
    -results
    -0.06
    levance
    -0.06
    ngx
    -0.06
    likes
    -0.05
     shutil
    -0.05
     acre
    -0.05
     dealership
    -0.05
    POSITIVE LOGITS
    Yeah
    0.07
    -Q
    0.07
    moduleName
    0.07
     distinctive
    0.06
    GRAPH
    0.06
     Sail
    0.06
     lately
    0.06
    (separator
    0.06
    .eulerAngles
    0.06
    IGHL
    0.06
    Activations Density 0.066%

    No Known Activations