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. 105684
    Prev
    Next
    INDEX
    Explanations

    website design

    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
    _prot
    -0.06
    -set
    -0.06
     scrapy
    -0.06
    /dev
    -0.06
     thru
    -0.06
    _version
    -0.06
    _Run
    -0.06
     pert
    -0.06
     warm
    -0.06
    人間
    -0.06
    POSITIVE LOGITS
     propiedad
    0.07
     ArgumentException
    0.06
    。」
    0.06
    ?”
    0.06
     Rolls
    0.06
     ---
    0.06
    刚才
    0.06
     supervised
    0.06
    <|begin_of_text|>
    0.06
    ANTLR
    0.06
    Activations Density 0.097%

    No Known Activations