© 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. 129540
    Prev
    Next
    INDEX
    Explanations

    ampersand character

    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
     ADS
    -0.07
     Pride
    -0.07
    	base
    -0.07
    938
    -0.07
     списка
    -0.07
     brutally
    -0.06
    [N
    -0.06
    <n
    -0.06
     punches
    -0.06
    /static
    -0.06
    POSITIVE LOGITS
    ους
    0.06
     LARGE
    0.06
    ......
    0.06
    كات
    0.06
    ecause
    0.06
    Results
    0.06
    SEE
    0.06
     milf
    0.06
     linebacker
    0.06
    리아
    0.06
    Activations Density 0.004%

    No Known Activations