© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126039
    Prev
    Next
    INDEX
    Explanations

    finances

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of revenue-related financial terms (e.g., “revenue,” “fees,” “commissions”).

    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
    
    -0.06
    
    -0.06
     selects
    -0.06
     eliminate
    -0.06
    _boundary
    -0.06
    .#
    -0.06
    ListModel
    -0.06
    _bit
    -0.06
    367
    -0.06
     decoding
    -0.06
    POSITIVE LOGITS
    posables
    0.08
     Char
    0.07
    wake
    0.07
    .loggedIn
    0.07
     springfox
    0.06
    년
    0.06
    .Seek
    0.06
    -Star
    0.06
     самостоятельно
    0.06
     obs
    0.06
    Activations Density 0.013%

    No Known Activations