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. 27403
    Prev
    Next
    INDEX
    Explanations

    earlier

    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
    tí
    -0.08
     opioid
    -0.08
    @nate
    -0.07
    Lua
    -0.07
     condemnation
    -0.07
    ("{}
    -0.07
    ulas
    -0.07
    кта
    -0.07
     Brent
    -0.07
    119
    -0.07
    POSITIVE LOGITS
     earlier
    0.14
     Earlier
    0.13
    Earlier
    0.11
     early
    0.11
     Early
    0.10
    Early
    0.10
     EAR
    0.08
     sooner
    0.08
     frü
    0.08
    arser
    0.08
    Activations Density 0.021%

    No Known Activations