© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109803
    Prev
    Next
    INDEX
    Explanations

    analysis

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the root “analys/​analyz,” i.e. words related to analysis or analyzing.

    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
    Fort
    -0.08
     Ford
    -0.07
    forg
    -0.07
    .StretchImage
    -0.07
    $t
    -0.07
     '"
    -0.07
    proper
    -0.07
    -football
    -0.06
     Sending
    -0.06
     Ecc
    -0.06
    POSITIVE LOGITS
     analysis
    0.16
     Analysis
    0.14
     analyze
    0.12
     analyzed
    0.11
     analyse
    0.11
    Analysis
    0.11
     analyses
    0.10
     analyzing
    0.10
    analysis
    0.10
     Analyzer
    0.10
    Activations Density 0.060%

    No Known Activations