© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41507
    Prev
    Next
    INDEX
    Explanations

    Time

    np_max-act · gemini-2.0-flash

    It detects references to ages or other explicit time markers (e.g. “age,” “time,” “moment,” “future”).

    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
    ,t
    -0.07
    ++,
    -0.07
    इस
    -0.07
     },
    ↵
    ↵
    -0.06
    plen
    -0.06
    보고
    -0.06
    싸
    -0.06
    기를
    -0.06
    typeof
    -0.06
    ,d
    -0.06
    POSITIVE LOGITS
    LIGHT
    0.07
     transports
    0.07
     MMP
    0.07
     µ
    0.06
    omid
    0.06
    uary
    0.06
    .Schedule
    0.06
    .allocate
    0.06
     VI
    0.06
    IsUnicode
    0.06
    Activations Density 0.155%

    No Known Activations