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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 56974
    Prev
    Next
    INDEX
    Explanations

    INDIRECT

    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
    .testing
    -0.07
    asename
    -0.07
    -counter
    -0.07
    Can
    -0.06
    CC
    -0.06
     Critical
    -0.06
    iydi
    -0.06
     circulation
    -0.06
    innie
    -0.06
     oluyor
    -0.06
    POSITIVE LOGITS
     INDIRECT
    0.08
    	map
    0.07
     tph
    0.07
    (receiver
    0.06
    Vtbl
    0.06
    <c
    0.06
    :not
    0.06
    (control
    0.06
    	speed
    0.06
    	dfs
    0.06
    Activations Density 0.001%

    No Known Activations