© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68741
    Prev
    Next
    INDEX
    Explanations

    companies and industries

    np_max-act · gemini-2.0-flash

    This neuron flags mentions of the company’s target application domains—i.e. listing the various industries or sectors it serves.

    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
    /tools
    -0.06
    <char
    -0.06
    εβ
    -0.06
     booth
    -0.06
     powering
    -0.06
     unpack
    -0.06
    WARN
    -0.06
    وست
    -0.06
    ени
    -0.06
    ु
    -0.06
    POSITIVE LOGITS
     xếp
    0.07
    [array
    0.06
     intimidate
    0.06
    gy
    0.06
     dưỡng
    0.06
     unleashed
    0.06
    )o
    0.06
    233
    0.06
     restricted
    0.06
     kafka
    0.06
    Activations Density 0.056%

    No Known Activations