© 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. 127201
    Prev
    Next
    INDEX
    Explanations

    __

    np_max-act · gemini-2.0-flash

    tokens that mark the assistant's message header or the transition to an assistant response in the conversation.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    TM
    -0.06
     retarded
    -0.06
     spending
    -0.06
    ادة
    -0.06
     cyc
    -0.06
    取
    -0.06
     stav
    -0.06
    리
    -0.06
    DLL
    -0.06
     l
    -0.06
    POSITIVE LOGITS
    (series
    0.07
    >';↵↵
    0.07
     tiers
    0.06
    Furthermore
    0.06
     hops
    0.06
    _PF
    0.06
     jobId
    0.06
    _Copy
    0.06
    plr
    0.06
    _Label
    0.06
    Activations Density 0.044%

    No Known Activations