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. 24498
    Prev
    Next
    INDEX
    Explanations

    protein

    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
    }')
    -0.06
     covert
    -0.06
     toho
    -0.06
     устра
    -0.06
    _gift
    -0.06
    -image
    -0.06
     bude
    -0.06
    enty
    -0.06
    ']]]↵
    -0.06
    et
    -0.06
    POSITIVE LOGITS
     ##↵
    0.06
     reviewed
    0.06
     Fabric
    0.06
    Implemented
    0.06
    .JsonProperty
    0.06
     ΠΡ
    0.06
     pwd
    0.06
     Cousins
    0.06
     TN
    0.06
     常
    0.06
    Activations Density 0.001%

    No Known Activations