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. 23-RESID-POST-AA
    6. 7475
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çık
    -0.07
    _ma
    -0.06
     PropertyInfo
    -0.06
     async
    -0.06
    _alloc
    -0.06
     tits
    -0.06
    設備
    -0.06
     letra
    -0.06
     eyes
    -0.06
     enough
    -0.06
    POSITIVE LOGITS
     OCT
    0.06
    ْل
    0.06
    eksiyon
    0.06
     Corn
    0.06
     Ген
    0.06
     ingres
    0.06
     purposes
    0.06
     Chinese
    0.06
    Flush
    0.06
    liğine
    0.06
    Activations Density 0.004%

    No Known Activations