© 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. 87151
    Prev
    Next
    INDEX
    Explanations

    numeric values related to data analysis or statistical results

    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
    OffsetTable
    -0.07
    -0.07
    {}",
    -0.07
    libs
    -0.07
    698
    -0.07
    ijk
    -0.07
    okit
    -0.07
    ourcing
    -0.06
    ervice
    -0.06
    inish
    -0.06
    POSITIVE LOGITS
    uÅŁ
    0.07
    iola
    0.07
    anco
    0.06
    и
    0.06
    i
    0.06
    berman
    0.06
    ëĭ¤
    0.06
    ĵ
    0.06
    ukkan
    0.06
    ORIA
    0.06
    Activations Density 0.030%

    No Known Activations