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. 26535
    Prev
    Next
    INDEX
    Explanations

    transporting supplies

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on words referring to aerial transport and delivery (e.g. helicopter flights delivering supplies or rescue).

    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
     manufacture
    -0.08
    indr
    -0.07
     fds
    -0.07
     equivalents
    -0.06
     trial
    -0.06
    .dylib
    -0.06
    ListAdapter
    -0.06
    Fan
    -0.06
     blind
    -0.06
    得到
    -0.06
    POSITIVE LOGITS
     název
    0.06
     가장
    0.06
     스
    0.06
    恶
    0.06
    tempt
    0.06
     vaguely
    0.06
    _Ph
    0.06
         
    0.06
     Bat
    0.06
     пля
    0.06
    Activations Density 0.021%

    No Known Activations