© 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. 25285
    Prev
    Next
    INDEX
    Explanations

    spoiled

    np_max-act · gemini-2.0-flash

    This neuron does not reliably activate for any text patterns—it remains inactive and thus does not detect any specific feature.

    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
     sampling
    -0.07
    ductor
    -0.07
    ampie
    -0.06
    狼
    -0.06
     purified
    -0.06
    Construct
    -0.06
    观
    -0.06
    عداد
    -0.06
    .д
    -0.06
     मर
    -0.06
    POSITIVE LOGITS
     Filip
    0.07
     COL
    0.07
     ServletException
    0.06
    .pt
    0.06
     privilege
    0.06
    DOB
    0.06
     Francie
    0.06
     guidance
    0.06
     teď
    0.06
    Persistent
    0.06
    Activations Density 0.011%

    No Known Activations