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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RESID-POST-AA
    6. 70143
    Prev
    Next
    INDEX
    Explanations

    uptake

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anners
    -0.07
    まず
    -0.07
    abcdefgh
    -0.06
     paramName
    -0.06
    ldb
    -0.06
    erals
    -0.06
    نى
    -0.06
    إن
    -0.06
    arsed
    -0.06
     cham
    -0.06
    POSITIVE LOGITS
     uptake
    0.18
    ke
    0.08
     Pep
    0.08
    <Value
    0.08
     mere
    0.07
     caravan
    0.07
    ake
    0.07
    _offer
    0.07
     womb
    0.07
     Sustainable
    0.07
    Activations Density 0.002%

    No Known Activations