© 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. 125266
    Prev
    Next
    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash

    the execution methods of scripts in a shell environment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    the main thing this neuron does is spot key domain‐object nouns—technical entities like “record,” “task,” “pages,” “documents,” or “agents.”

    oai_token-act-pair · o4-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
    ih
    -0.07
     fy
    -0.07
    ש
    -0.07
    !--
    -0.06
    용
    -0.06
    Know
    -0.06
    likle
    -0.06
     Iron
    -0.06
    하려
    -0.06
    ordes
    -0.06
    POSITIVE LOGITS
    .parseFloat
    0.07
     Fl
    0.06
    getList
    0.06
    ações
    0.06
    ницип
    0.06
     oggi
    0.06
     Đảng
    0.06
    .cols
    0.06
     mapa
    0.06
    =======↵
    0.06
    Activations Density 0.211%

    No Known Activations