© 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. 126658
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric values expressed as floating‐point decimals (e.g., “0.284”, “1.989”, “0.2375”).

    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
     CSRF
    -0.07
     MessageType
    -0.06
     حضرت
    -0.06
    <ActionResult
    -0.06
     Audience
    -0.06
     Parsing
    -0.06
     PendingIntent
    -0.06
     sims
    -0.06
    Planning
    -0.06
     validationResult
    -0.06
    POSITIVE LOGITS
    oday
    0.07
    애
    0.07
     partie
    0.07
    ены
    0.06
     thật
    0.06
    elman
    0.06
    thy
    0.06
    Creat
    0.06
     Özel
    0.06
    insky
    0.06
    Activations Density 0.055%

    No Known Activations