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. 7-RESID-POST-AA
    6. 93175
    Prev
    Next
    INDEX
    Explanations

    numbers in scientific results

    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
    ेस
    -0.06
    UEL
    -0.06
    ンの
    -0.06
    EAR
    -0.06
    IRCLE
    -0.06
    ListOf
    -0.06
    Recogn
    -0.06
    moz
    -0.06
    	old
    -0.06
    "She
    -0.05
    POSITIVE LOGITS
     Bonds
    0.07
     iç
    0.07
    조
    0.07
    }↵↵↵↵↵
    0.07
     fascinating
    0.06
     subconscious
    0.06
     condom
    0.06
    _decrypt
    0.06
     lizard
    0.06
     réfé
    0.06
    Activations Density 0.053%

    No Known Activations