© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 14551
    Prev
    Next
    INDEX
    Explanations

    choking

    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
     поб
    -0.06
     лучше
    -0.06
    letcher
    -0.06
     substituted
    -0.06
     mě
    -0.06
    ふ
    -0.06
    -mouth
    -0.06
    	dis
    -0.06
    241
    -0.06
     درباره
    -0.06
    POSITIVE LOGITS
    plor
    0.06
    (AP
    0.06
     AS
    0.06
    .listener
    0.06
     신입
    0.06
    (des
    0.06
    気
    0.06
    ğin
    0.06
    (components
    0.06
    eing
    0.06
    Activations Density 0.002%

    No Known Activations