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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RESID-POST-AA
    6. 93457
    Prev
    Next
    INDEX
    Explanations

    fundraising events

    np_max-act · gemini-2.0-flash

    phrases and keywords related to team fundraising and charity events.

    oai_token-act-pair · gpt-4oTriggered by @tcai
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NavBar
    -0.07
    تها
    -0.07
    	Editor
    -0.07
    .getContentPane
    -0.07
    .www
    -0.06
    scripts
    -0.06
    bec
    -0.06
    ΑΤ
    -0.06
    esen
    -0.06
    Ts
    -0.06
    POSITIVE LOGITS
     delta
    0.07
     interpersonal
    0.06
     supplementary
    0.06
     distinguished
    0.06
     distinguishing
    0.06
    spent
    0.06
    �다
    0.06
     chỗ
    0.06
     vysoké
    0.06
    MRI
    0.06
    Activations Density 0.068%

    No Known Activations