© 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. 12703
    Prev
    Next
    INDEX
    Explanations

    Exception

    np_max-act · gemini-2.0-flash

    The neuron never activates on any tokens—i.e. it’s effectively inactive and does not detect any pattern.

    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
    된
    -0.06
    .dis
    -0.06
    zech
    -0.06
    imators
    -0.06
     mathematics
    -0.06
    valu
    -0.06
    册
    -0.06
     شع
    -0.06
    ५
    -0.06
    icity
    -0.06
    POSITIVE LOGITS
     Exception
    0.08
    Exceptions
    0.08
    Exception
    0.07
    梯
    0.07
     toppings
    0.07
     viewpoint
    0.07
    _CONDITION
    0.07
     Yüksek
    0.07
     Expenses
    0.07
    Everybody
    0.07
    Activations Density 0.001%

    No Known Activations