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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 10520
    Prev
    Next
    INDEX
    Explanations

    Dates and years

    np_max-act · gemini-2.0-flash

    tokens that indicate dates, years, or historical/timeline markers.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    (KEY
    -0.06
    Clar
    -0.05
    .PL
    -0.05
    ]]></
    -0.05
     resemble
    -0.05
    ωδ
    -0.05
     refers
    -0.05
    <link
    -0.05
     PNG
    -0.05
    urrect
    -0.05
    POSITIVE LOGITS
    -position
    0.07
     unser
    0.07
     сух
    0.07
    ِه
    0.07
     ancestors
    0.07
    高校
    0.07
    sson
    0.07
     příro
    0.06
     výše
    0.06
     LENGTH
    0.06
    Activations Density 23.924%

    No Known Activations