© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 52047
    Prev
    Next
    INDEX
    Explanations

    Future tense/"will"

    np_max-act · gemini-2.0-flash
    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
    设计器
    -0.07
     placed
    -0.06
    ded
    -0.06
    �
    -0.06
    aised
    -0.06
     named
    -0.06
     validations
    -0.06
     نس
    -0.06
    CEF
    -0.06
    820
    -0.06
    POSITIVE LOGITS
    uthor
    0.07
    <|eot_id|>
    0.07
    estro
    0.07
     rebellion
    0.06
     przypad
    0.06
    ाज
    0.06
     випад
    0.06
    (time
    0.06
     VIN
    0.06
     Spo
    0.06
    Activations Density 0.053%

    No Known Activations