© 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. 115505
    Prev
    Next
    INDEX
    Explanations

    False assumptions

    np_max-act · gemini-2.0-flash

    tokens that are personal pronouns and their nearby auxiliary/main verbs in statements expressing a speaker's claim or assertion.

    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
     Cached
    -0.07
    ENG
    -0.06
    。↵↵
    -0.06
    кра
    -0.06
     bespoke
    -0.06
    onth
    -0.06
     Dj
    -0.06
    apps
    -0.06
     procure
    -0.06
    화
    -0.06
    POSITIVE LOGITS
     aller
    0.07
    (always
    0.07
     vintage
    0.07
    cannot
    0.06
    TERN
    0.06
    quality
    0.06
     Lutheran
    0.06
    [array
    0.06
    xsd
    0.06
     Fellow
    0.06
    Activations Density 0.037%

    No Known Activations