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. 77494
    Prev
    Next
    INDEX
    Explanations

    Google applications

    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
    mond
    -0.07
     leaking
    -0.07
     Methodist
    -0.07
    626
    -0.07
     IBM
    -0.07
    navigator
    -0.07
     equival
    -0.06
    669
    -0.06
    .datasets
    -0.06
    raits
    -0.06
    POSITIVE LOGITS
     (;;)
    0.06
    .ReadKey
    0.06
     distinctions
    0.06
     occasional
    0.06
     sinister
    0.06
    {}↵↵
    0.06
     FixedUpdate
    0.06
     Oyun
    0.06
     devuelve
    0.06
     /=
    0.06
    Activations Density 0.036%

    No Known Activations