© 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. 91947
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any token.

    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
    agraph
    -0.06
     Yellow
    -0.06
    achsen
    -0.06
     informací
    -0.06
    erva
    -0.06
     образования
    -0.06
    acija
    -0.05
     slightest
    -0.05
    _Service
    -0.05
    810
    -0.05
    POSITIVE LOGITS
     conjug
    0.08
     filtered
    0.07
     defer
    0.07
    締
    0.06
     кад
    0.06
    [char
    0.06
    ิทธ
    0.06
    <Employee
    0.06
    'av
    0.06
    Qual
    0.06
    Activations Density 0.077%

    No Known Activations