© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61371
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns related to individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.07
    ondo
    -0.07
    Ä°ÅŁ
    -0.06
    ãĤ¹ãĤ¿ãĥ¼
    -0.06
    æľ¬å½ĵ
    -0.06
    blems
    -0.06
    blem
    -0.06
    aling
    -0.06
    ãĤĨ
    -0.06
    лаб
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.08
     migrationBuilder
    0.07
    raquo
    0.07
    ponsored
    0.06
    @show
    0.06
     Subscriber
    0.06
    [email
    0.06
    iser
    0.06
    .github
    0.06
    .mount
    0.06
    Activations Density 0.013%

    No Known Activations