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. 15-RESID-POST-AA
    6. 91524
    Prev
    Next
    INDEX
    Explanations

    Estonian

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _checks
    -0.07
     Criteria
    -0.07
    Bur
    -0.07
    يب
    -0.07
     thương
    -0.07
     PIPE
    -0.07
     기술
    -0.07
    ial
    -0.07
    ListNode
    -0.07
     Griffin
    -0.06
    POSITIVE LOGITS
    젠
    0.07
     enam
    0.06
    über
    0.06
     cialis
    0.06
     ทอง
    0.06
    licted
    0.06
    lesh
    0.06
     cuck
    0.06
     koc
    0.05
    rud
    0.05
    Activations Density 0.028%

    No Known Activations