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. 12787
    Prev
    Next
    INDEX
    Explanations

    reduced

    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
     Boot
    -0.07
     материал
    -0.07
    αιν
    -0.06
     sollen
    -0.06
     tamaño
    -0.06
     zoekt
    -0.06
    inate
    -0.06
     Александ
    -0.06
    	q
    -0.06
     doktor
    -0.06
    POSITIVE LOGITS
    '],$
    0.07
    (filtered
    0.07
     subsequ
    0.07
     Sweet
    0.07
    Converter
    0.07
    _FUNCTION
    0.07
     інт
    0.06
     lookup
    0.06
    众
    0.06
    (startTime
    0.06
    Activations Density 0.000%

    No Known Activations