© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 104766
    Prev
    Next
    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash

    instructions related to data migration processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    ΣΤ
    -0.07
     المك
    -0.07
     Islamabad
    -0.07
    DCALL
    -0.07
    sprintf
    -0.06
     spirited
    -0.06
     Pathfinder
    -0.06
    Caught
    -0.06
     Cupertino
    -0.06
     Jacqu
    -0.06
    POSITIVE LOGITS
    .folder
    0.07
    member
    0.06
     Lyon
    0.06
     dean
    0.06
     cheats
    0.06
    (";
    0.05
     &&
    0.05
    (from
    0.05
     ns
    0.05
     DD
    0.05
    Activations Density 0.139%

    No Known Activations