Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1095
    Prev
    Next
    INDEX
    Explanations

    final

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “final” or “Finals,” i.e. references to championship or concluding matches.

    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
    Col
    -0.07
     buff
    -0.07
    addChild
    -0.06
    ull
    -0.06
    igram
    -0.06
    ediator
    -0.06
    bairro
    -0.06
    fff
    -0.06
    ACT
    -0.06
     type
    -0.06
    POSITIVE LOGITS
     velmi
    0.07
     finals
    0.07
     nationwide
    0.07
    ansas
    0.06
     FileNotFoundError
    0.06
     Finals
    0.06
     FString
    0.06
     jusqu
    0.06
    เลย
    0.06
     phoenix
    0.06
    Activations Density 0.012%

    No Known Activations