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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 85940
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of coverage “through being struck by an automobile,” i.e. the specific phrase describing loss “by being struck by an automobile.”

    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
    Functional
    -0.07
     Laz
    -0.06
     reacting
    -0.06
    _expand
    -0.06
    �
    -0.06
     Truy
    -0.06
    .paging
    -0.06
     humor
    -0.06
    (command
    -0.06
    Walker
    -0.06
    POSITIVE LOGITS
    [date
    0.07
    pring
    0.06
    avatars
    0.06
    рит
    0.06
     Kos
    0.06
     eget
    0.06
    _TEST
    0.06
    228
    0.06
    RE
    0.06
     Ghana
    0.06
    Activations Density 0.041%

    No Known Activations