Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84572
    Prev
    Next
    INDEX
    Explanations

    time periods

    np_max-act · gemini-2.0-flash

    This neuron detects numeric expressions indicating time intervals (e.g., counts of days, years, months).

    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
    leşik
    -0.06
     BATCH
    -0.06
     bilgisayar
    -0.06
     zvlášt
    -0.06
    _PEER
    -0.06
     Mighty
    -0.06
    English
    -0.06
    ารย
    -0.06
     GOODMAN
    -0.05
    _segments
    -0.05
    POSITIVE LOGITS
    ratings
    0.08
     agg
    0.07
    ','%
    0.07
     pushing
    0.06
    어가
    0.06
     alg
    0.06
    時代
    0.06
     dod
    0.06
    _working
    0.06
    斷
    0.06
    Activations Density 0.025%

    No Known Activations