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. 11-RESID-POST-AA
    6. 100908
    Prev
    Next
    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash

    the names of authors or significant figures associated with various historical, scientific, or academic disciplines.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -0.09
     Retirement
    -0.08
     segundos
    -0.08
     цар
    -0.07
    λίου
    -0.07
    7
    -0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.07
    _dropdown
    -0.07
     手
    -0.07
     Playstation
    -0.07
    POSITIVE LOGITS
    						
    ↵
    0.08
    Uri
    0.07
     loosen
    0.07
     Colum
    0.07
    McC
    0.07
     McC
    0.07
     edil
    0.07
     Dwight
    0.07
     ascertain
    0.06
    quotelev
    0.06
    Activations Density 0.081%

    No Known Activations