Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 93126
    Prev
    Next
    INDEX
    Explanations

    SSE/SSE2 instructions and code

    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
     Rings
    -0.07
    Pipe
    -0.07
    EntryPoint
    -0.07
     CASCADE
    -0.07
    "G
    -0.07
    }_{
    -0.07
     UIResponder
    -0.06
     tolik
    -0.06
    zek
    -0.06
     spike
    -0.06
    POSITIVE LOGITS
    oubtedly
    0.07
     famously
    0.06
    ComputedStyle
    0.06
     노출등록
    0.06
     transitions
    0.06
     감
    0.06
    stringLiteral
    0.06
     paramount
    0.06
    ôm
    0.06
     actualizar
    0.06
    Activations Density 0.007%

    No Known Activations