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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56968
    Prev
    Next
    INDEX
    Explanations

    companies and firms

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of business or organizational entities (company/firm/consulting names and related founder/owner/consultant roles).

    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
    :${
    -0.07
    production
    -0.07
    ufac
    -0.07
    'E
    -0.06
    ла
    -0.06
     develop
    -0.06
    楽し
    -0.06
     Gospel
    -0.06
    _b
    -0.06
    Posting
    -0.06
    POSITIVE LOGITS
    icias
    0.08
    (dim
    0.07
     raised
    0.07
     defaultManager
    0.06
     capita
    0.06
    .Cons
    0.06
     Triumph
    0.06
    .matmul
    0.06
    Ú
    0.06
     anonymous
    0.06
    Activations Density 0.029%

    No Known Activations