© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 1739
    Prev
    Next
    INDEX
    Explanations

    who

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condemnation
    -0.07
    esto
    -0.07
     случа
    -0.07
    .staff
    -0.06
     swell
    -0.06
     lite
    -0.06
    하자
    -0.06
    スレ
    -0.06
    _folders
    -0.06
    fasta
    -0.06
    POSITIVE LOGITS
     pair
    0.07
     Monthly
    0.07
    노출
    0.07
     projections
    0.06
    	Int
    0.06
    itives
    0.06
     Ram
    0.06
     stayed
    0.06
    견
    0.06
     captains
    0.06
    Activations Density 0.012%

    No Known Activations