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. 125224
    Prev
    Next
    INDEX
    Explanations

    title

    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
    .debugLine
    -0.07
    …and
    -0.06
     highways
    -0.06
    "She
    -0.06
     diye
    -0.06
    HttpException
    -0.06
    .Fl
    -0.06
     uzak
    -0.06
    proposal
    -0.06
    	the
    -0.06
    POSITIVE LOGITS
     downside
    0.07
    548
    0.06
    514
    0.06
     Tier
    0.06
     Tide
    0.06
    MODE
    0.06
    SQ
    0.06
     fashionable
    0.06
    325
    0.06
     tackle
    0.06
    Activations Density 0.002%

    No Known Activations