© 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. 126402
    Prev
    Next
    INDEX
    Explanations

    technical issues and debugging

    np_max-act · gemini-2.0-flash

    The neuron activates on numbered list markers and their surrounding explanatory tokens (e.g. “1.”, “2.”, “The”, and other words in step-by-step technical explanations).

    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
     Hipp
    -0.06
     many
    -0.06
    001
    -0.06
     gd
    -0.06
    munition
    -0.06
     Decrypt
    -0.06
    tah
    -0.05
    ュ
    -0.05
    óc
    -0.05
     NAS
    -0.05
    POSITIVE LOGITS
    airo
    0.07
     carbs
    0.07
     sque
    0.06
     blockers
    0.06
     decorator
    0.06
    sup
    0.06
     م
    0.06
    uben
    0.06
    ehir
    0.06
     emp
    0.06
    Activations Density 0.040%

    No Known Activations