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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 126558
    Prev
    Next
    INDEX
    Explanations

    generic object/item reference

    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
    _HAVE
    -0.07
    pq
    -0.06
     Following
    -0.06
    PP
    -0.06
    	has
    -0.06
    Been
    -0.06
    Q
    -0.06
    _EC
    -0.06
     PVOID
    -0.06
     пока
    -0.06
    POSITIVE LOGITS
     deliberate
    0.07
     Dortmund
    0.07
     subdir
    0.07
     респ
    0.07
    cntl
    0.07
    何
    0.07
    agen
    0.06
     المل
    0.06
     쿠
    0.06
    agina
    0.06
    Activations Density 0.003%

    No Known Activations