© 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. 19-RESID-POST-AA
    6. 87346
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    places in the text that mark or begin numbered list items (enumeration markers like "1.", "2.", "3.", etc.).

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Retrieve
    -0.07
    保護
    -0.07
    ifference
    -0.06
    @store
    -0.06
    (st
    -0.06
    フ�
    -0.06
     keto
    -0.06
     Carlo
    -0.06
     bulld
    -0.06
    итив
    -0.06
    POSITIVE LOGITS
     disappointment
    0.06
     whopping
    0.06
    浜
    0.06
     Plumbing
    0.06
     tumble
    0.06
     downstairs
    0.06
     FLAGS
    0.06
     breeds
    0.06
    (AT
    0.06
     مشارکت
    0.06
    Activations Density 0.030%

    No Known Activations