© 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. 15-RESID-POST-AA
    6. 23025
    Prev
    Next
    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash

    Instances of the word "past" used as a temporal marker (e.g., "the past ...", "in the past ...") indicating recent time periods.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [level
    -0.06
     Loader
    -0.06
     Innoc
    -0.06
     connectors
    -0.06
     điều
    -0.06
    $j
    -0.06
     zombie
    -0.06
    _modifier
    -0.06
    .getStringExtra
    -0.06
     Lime
    -0.06
    POSITIVE LOGITS
     past
    0.15
    Past
    0.11
     Past
    0.11
    past
    0.11
    _past
    0.09
    ESH
    0.08
    ST
    0.07
     scout
    0.07
    яться
    0.07
    امه
    0.07
    Activations Density 0.016%

    No Known Activations