© 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. 126065
    Prev
    Next
    INDEX
    Explanations

    incremental increase

    np_max-act · gemini-2.0-flash

    The neuron detects language that signals progressive buildup in training—words about gradually increasing intensity, duration, or difficulty.

    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
    sword
    -0.07
    offer
    -0.07
    ήμερα
    -0.07
    aza
    -0.06
    shield
    -0.06
    .Site
    -0.06
    ользов
    -0.06
    ucht
    -0.06
     vos
    -0.06
     stopped
    -0.06
    POSITIVE LOGITS
     Electron
    0.07
    트
    0.07
     Meeting
    0.06
    epsilon
    0.06
     Compliance
    0.06
     ".";↵
    0.06
    付
    0.06
     powerless
    0.06
    .xlim
    0.06
    rapy
    0.06
    Activations Density 0.010%

    No Known Activations