© 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
    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. 102188
    Prev
    Next
    INDEX
    Explanations

    funding/investment

    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
     بين
    -0.07
     Cob
    -0.07
    بيع
    -0.06
     nargs
    -0.06
    _VERSION
    -0.06
    908
    -0.06
     proclaim
    -0.06
    ılıp
    -0.06
     Mercury
    -0.06
     Unsupported
    -0.06
    POSITIVE LOGITS
     internet
    0.06
    ICLES
    0.06
    pcl
    0.06
    alet
    0.06
    PING
    0.06
     lawful
    0.06
    ature
    0.06
     dilemma
    0.06
     Window
    0.06
    ?>↵↵↵
    0.06
    Activations Density 0.000%

    No Known Activations