Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 104114
    Prev
    Next
    INDEX
    Explanations

    introducing new concepts

    np_max-act · gemini-2.0-flash

    phrases related to statistical concepts and methodologies.

    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
    >>↵↵
    -0.07
    .__
    -0.06
    .setX
    -0.06
    _pod
    -0.06
    .Auth
    -0.06
    .bounds
    -0.06
    GetInstance
    -0.06
    ([('
    -0.06
     yPos
    -0.06
    _Statics
    -0.06
    POSITIVE LOGITS
    inee
    0.07
    etrize
    0.07
    anned
    0.07
    scanf
    0.07
     coherence
    0.06
    urr
    0.06
     提
    0.06
    abytes
    0.06
     ',
    0.06
    ması
    0.06
    Activations Density 0.044%

    No Known Activations