© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 125536
    Prev
    Next
    INDEX
    Explanations

    post

    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
    _squared
    -0.07
     fragmented
    -0.06
    etes
    -0.06
    NgModule
    -0.06
    ाकर
    -0.06
     magazines
    -0.06
    variable
    -0.06
    _pk
    -0.06
    <|start_header_id|>
    -0.06
    πο
    -0.06
    POSITIVE LOGITS
    getJSON
    0.10
     LLVM
    0.07
    544
    0.07
    .Business
    0.07
    _CPP
    0.07
    	vector
    0.07
    hma
    0.07
     zost
    0.06
     GetCurrent
    0.06
    []>(
    0.06
    Activations Density 0.001%

    No Known Activations