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. 122510
    Prev
    Next
    INDEX
    Explanations

    News quotes

    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_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
    Für
    -0.06
    648
    -0.06
     میتوان
    -0.06
    Ι
    -0.06
     enemy
    -0.06
    track
    -0.06
     dr
    -0.06
    631
    -0.06
     multiplied
    -0.05
    firm
    -0.05
    POSITIVE LOGITS
     tls
    0.06
    	retval
    0.06
     maneu
    0.06
     Lecture
    0.06
    ’ye
    0.06
     Xt
    0.06
    gressive
    0.06
     Gord
    0.06
     serm
    0.06
     dém
    0.06
    Activations Density 0.056%

    No Known Activations