© 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. 11-RESID-POST-AA
    6. 20966
    Prev
    Next
    INDEX
    Explanations

    guidance/advice

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -INF
    -0.07
     GestureDetector
    -0.06
     IGN
    -0.06
    선을
    -0.06
    collectionView
    -0.06
     rows
    -0.06
    WINDOW
    -0.06
     presently
    -0.06
     쉬
    -0.06
     '''↵↵
    -0.06
    POSITIVE LOGITS
    áhnout
    0.07
    irection
    0.07
     entropy
    0.06
     hc
    0.06
    Endpoint
    0.06
     Limited
    0.06
    Copy
    0.06
    oria
    0.06
    itative
    0.06
     teknik
    0.06
    Activations Density 0.193%

    No Known Activations