© 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. 80066
    Prev
    Next
    INDEX
    Explanations

    as it happens

    np_max-act · gemini-2.0-flash

    words related to chemical reactions and processes in organic chemistry.

    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
    been
    -0.07
     многие
    -0.06
     vice
    -0.06
     testcase
    -0.06
     گی
    -0.06
     Ngân
    -0.06
    marvin
    -0.06
    ernet
    -0.06
     Rak
    -0.06
    ワー
    -0.06
    POSITIVE LOGITS
     TASK
    0.07
    .quick
    0.07
    .event
    0.07
     extinct
    0.07
    .Ab
    0.07
     candle
    0.07
     Seite
    0.07
    _trap
    0.07
    _funcs
    0.07
     darkness
    0.07
    Activations Density 0.066%

    No Known Activations