© 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. 76774
    Prev
    Next
    INDEX
    Explanations

    references to news organizations and significant numerical data

    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
    urovision
    -0.08
    cstdint
    -0.06
    iosa
    -0.06
    æģµ
    -0.06
    ìŀĦ
    -0.06
    elik
    -0.06
    stru
    -0.06
    orWhere
    -0.06
    .setDefault
    -0.06
     Geh
    -0.06
    POSITIVE LOGITS
     CNN
    0.09
    CNN
    0.09
     cnn
    0.08
    ftime
    0.07
     ServiceException
    0.07
    verb
    0.06
    lauf
    0.06
    oley
    0.06
     ЧаÑģ
    0.06
     Masks
    0.06
    Activations Density 0.022%

    No Known Activations