© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128696
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially version numbers and decimal values.

    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
     Eine
    -0.07
    D
    -0.06
    行动
    -0.06
    .glide
    -0.06
    .hashCode
    -0.06
    jších
    -0.06
    uco
    -0.06
    Ds
    -0.06
     vữ
    -0.06
     anal
    -0.06
    POSITIVE LOGITS
     Gaz
    0.07
    _membership
    0.06
     payoff
    0.06
    �
    0.06
    ='./
    0.06
    -clean
    0.06
    .Pay
    0.06
     IRepository
    0.06
    „N
    0.06
     Karma
    0.06
    Activations Density 0.186%

    No Known Activations