© 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. 126268
    Prev
    Next
    INDEX
    Explanations

    technical topics

    np_max-act · gemini-2.0-flash

    The neuron preferentially activates on longer, less common content words—especially specialized or technical terms.

    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
     scrim
    -0.07
     plaintext
    -0.07
     administration
    -0.07
    slug
    -0.06
    .integration
    -0.06
     BTS
    -0.06
    outline
    -0.06
     capitalize
    -0.06
     FN
    -0.06
     Д
    -0.06
    POSITIVE LOGITS
    )

↵
    0.07
     Mockito
    0.06
    (',')
    0.06
    xCA
    0.06
     Parse
    0.06
    coeff
    0.06
    uses
    0.06
     możli
    0.06
     رسول
    0.05
     نسمة
    0.05
    Activations Density 0.743%

    No Known Activations