© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82792
    Prev
    Next
    INDEX
    Explanations

    references to specific phrases and punctuation that punctuate significant themes

    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
    .dispatcher
    -0.06
    elon
    -0.06
    ported
    -0.06
    uin
    -0.06
     such
    -0.06
    ylie
    -0.06
    andon
    -0.06
    ONGL
    -0.06
     similarly
    -0.05
    rob
    -0.05
    POSITIVE LOGITS
    zeit
    0.08
     seedu
    0.08
    .opend
    0.07
    iesen
    0.07
    isible
    0.07
    cete
    0.07
    ALCHEMY
    0.07
     ones
    0.07
    ä¹ĭä¸Ģ
    0.07
    avou
    0.07
    Activations Density 0.049%

    No Known Activations