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. 110655
    Prev
    Next
    INDEX
    Explanations

    outputs

    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
    Texto
    -0.07
     quel
    -0.06
     سبب
    -0.06
    Metal
    -0.06
    floor
    -0.06
     males
    -0.06
    .fun
    -0.06
     cel
    -0.06
     sexuality
    -0.06
     champions
    -0.06
    POSITIVE LOGITS
    _KERNEL
    0.07
    ,从
    0.06
    UY
    0.06
    .Points
    0.06
     Що
    0.06
    -tech
    0.06
    IndexOf
    0.06
     softmax
    0.06
    oky
    0.06
    -products
    0.06
    Activations Density 0.007%

    No Known Activations