© 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. 61333
    Prev
    Next
    INDEX
    Explanations

    references to uncertainty and the need for more information or clarity

    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
     previously
    -0.07
     Previously
    -0.06
    onte
    -0.06
    .Fields
    -0.06
    eldo
    -0.06
    олиÑĤ
    -0.06
    ucht
    -0.06
    erno
    -0.06
    raman
    -0.06
    atism
    -0.06
    POSITIVE LOGITS
     actual
    0.07
     data
    0.07
    AGO
    0.07
    ega
    0.07
    actual
    0.07
     official
    0.06
     final
    0.06
    avid
    0.06
    ADATA
    0.06
     verileri
    0.06
    Activations Density 0.026%

    No Known Activations