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. 84787
    Prev
    Next
    INDEX
    Explanations

    film

    np_max-act · gemini-2.0-flash

    The neuron detects references to movies and television content (e.g. film/series titles and media category words).

    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
     Hearts
    -0.07
    olutely
    -0.06
     hardwood
    -0.06
    <{
    -0.06
     ville
    -0.06
    INTERNAL
    -0.06
    Deg
    -0.06
    ищ
    -0.06
    .REQUEST
    -0.06
     світ
    -0.06
    POSITIVE LOGITS
    _subplot
    0.07
    immutable
    0.07
     влия
    0.07
    ↵↵↵↵↵↵
    0.07
     акку
    0.07
    ỏ
    0.07
     agitation
    0.07
     ::↵
    0.06
     Jedi
    0.06
    Chain
    0.06
    Activations Density 0.028%

    No Known Activations