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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 104449
    Prev
    Next
    INDEX
    Explanations

    coding and math

    np_max-act · gemini-2.0-flash

    evaluative statements about social behaviors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cheeks
    -0.07
     Riv
    -0.07
    Locale
    -0.07
    -phone
    -0.06
    UIView
    -0.06
    _answers
    -0.06
     antig
    -0.06
     Chúng
    -0.06
     lashes
    -0.06
     letra
    -0.06
    POSITIVE LOGITS
     DONE
    0.07
    _DST
    0.07
    ле
    0.06
    ISR
    0.06
     ----------------------------------------------------------------------↵
    0.06
    产业
    0.06
    翻
    0.06
     Modifier
    0.06
     mandated
    0.06
    イツ
    0.06
    Activations Density 0.001%

    No Known Activations