© 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. 15-LLAMASCOPE-RES-131K
    11. 61637
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and closing syntax elements in code snippets

    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
     mini
    -0.07
    .scalablytyped
    -0.07
    hoe
    -0.07
    NSE
    -0.06
    ucci
    -0.06
    vie
    -0.06
    mess
    -0.06
    idal
    -0.06
    tel
    -0.06
    WithIdentifier
    -0.06
    POSITIVE LOGITS
    eldo
    0.08
    ritch
    0.07
    apo
    0.06
     Rath
    0.06
    lesc
    0.06
    hin
    0.06
    axy
    0.06
    orthand
    0.06
    994
    0.06
     Shut
    0.06
    Activations Density 0.009%

    No Known Activations