© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    Code/technical instructions examples

    np_max-act · gemini-2.0-flash

    This neuron lights up on the template’s instruction lines—words that introduce or describe tools and usage (e.g. “Useful,” “Input,” “should,” etc.).

    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
    ary
    -0.06
     Partition
    -0.06
    ------------------------------
    -0.06
    INI
    -0.06
    align
    -0.06
    Stride
    -0.06
    Function
    -0.06
    .GetHashCode
    -0.06
     hus
    -0.06
    .write
    -0.06
    POSITIVE LOGITS
     khai
    0.07
    ใจ
    0.07
     amer
    0.07
     SMART
    0.06
     rural
    0.06
     divisor
    0.06
    ismus
    0.06
     گردش
    0.06
     Activ
    0.06
     ancestors
    0.06
    Activations Density 0.023%

    No Known Activations