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. 11-RESID-POST-AA
    6. 53142
    Prev
    Next
    INDEX
    Explanations

    small sizes

    np_max-act · gemini-2.0-flash

    technical terms related to the manufacturing and design of semiconductor devices.

    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
    alien
    -0.07
     cinemas
    -0.06
     Lamb
    -0.06
    Cad
    -0.06
    _redirected
    -0.06
     Journey
    -0.06
     Quest
    -0.06
     Imper
    -0.06
     visual
    -0.06
     Iranians
    -0.06
    POSITIVE LOGITS
     RecognitionException
    0.07
     tư
    0.07
    /
    ↵
    ↵
    0.07
     СССР
    0.07
     appellant
    0.07
     стос
    0.06
    [];
    ↵
    0.06
    []=
    0.06
     поэтому
    0.06
     раза
    0.06
    Activations Density 0.020%

    No Known Activations