© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 36992
    Prev
    Next
    INDEX
    Explanations

    medical warnings

    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
     shielding
    -0.07
    (""))
    -0.07
    _trap
    -0.07
    (ver
    -0.07
    Registro
    -0.07
     ankles
    -0.06
     bài
    -0.06
    adecimal
    -0.06
    _tickets
    -0.06
    amba
    -0.06
    POSITIVE LOGITS
    ]+\
    0.07
    ********************************************************************************
    0.06
    児
    0.06
     seront
    0.06
    -root
    0.06
    λμ
    0.06
     Concept
    0.06
    альну
    0.06
     RGB
    0.06
     Jens
    0.06
    Activations Density 0.021%

    No Known Activations