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. 15-RESID-POST-AA
    6. 722
    Prev
    Next
    INDEX
    Explanations

    abs

    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
    切り
    -0.06
     Levy
    -0.06
     Byte
    -0.06
     Petra
    -0.06
    okus
    -0.06
     été
    -0.06
    _ENTRY
    -0.06
     "@"
    -0.06
    .setResult
    -0.06
    larla
    -0.06
    POSITIVE LOGITS
     FileSystem
    0.07
    indeki
    0.07
    Дата
    0.07
    ]))↵↵
    0.07
    .lines
    0.07
     camel
    0.07
     lamp
    0.07
    )。↵↵
    0.06
    !!↵↵
    0.06
     learnt
    0.06
    Activations Density 0.001%

    No Known Activations