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. 41986
    Prev
    Next
    INDEX
    Explanations

    band tours

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of artists serving as opening or support acts on tour.

    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
    ію
    -0.07
    C
    -0.06
     Wu
    -0.06
     рекоменду
    -0.06
     موقعیت
    -0.06
     bus
    -0.06
    زان
    -0.06
     Latvia
    -0.06
     iPad
    -0.06
    博物
    -0.06
    POSITIVE LOGITS
    _secondary
    0.06
     illusions
    0.06
     λίγ
    0.06
     twitch
    0.06
    serde
    0.06
     agreement
    0.06
    IntervalSince
    0.06
    isbury
    0.06
     thuisontvangst
    0.06
     Under
    0.06
    Activations Density 0.002%

    No Known Activations