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. 104421
    Prev
    Next
    INDEX
    Explanations

    Tuning and optimization

    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_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
    accumulator
    -0.06
    SnackBar
    -0.06
     createSelector
    -0.06
     penc
    -0.06
    _review
    -0.06
    ้ผ
    -0.06
    ufreq
    -0.06
     yeter
    -0.06
    Rad
    -0.06
     Beng
    -0.06
    POSITIVE LOGITS
    -span
    0.08
    -zero
    0.07
    TEE
    0.07
     initWithNibName
    0.06
    oblins
    0.06
    бо
    0.06
     jon
    0.06
    although
    0.06
    тон
    0.06
     wizards
    0.06
    Activations Density 0.037%

    No Known Activations