© 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. 110149
    Prev
    Next
    INDEX
    Explanations

    want/need

    np_max-act · gemini-2.0-flash

    This neuron detects first‐person expressions of desire or need (e.g. “I want,” “I need”).

    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
     Koch
    -0.07
    ANGES
    -0.06
     Amazon
    -0.06
     preds
    -0.06
    ans
    -0.06
     International
    -0.06
    Logical
    -0.06
    setEnabled
    -0.06
     nghiệp
    -0.06
    .directory
    -0.06
    POSITIVE LOGITS
    TintColor
    0.07
     onu
    0.07
    /twitter
    0.06
    startIndex
    0.06
    plode
    0.06
     activations
    0.06
     emot
    0.06
    KeyName
    0.06
     TNT
    0.06
     myocard
    0.06
    Activations Density 0.028%

    No Known Activations