© 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. 71165
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references

    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
    aight
    -0.08
    napshot
    -0.07
    ampp
    -0.07
    ulling
    -0.07
     Vác
    -0.07
    ãĥŃãĥ¼
    -0.07
    uong
    -0.07
    ignon
    -0.07
     duro
    -0.07
    loon
    -0.07
    POSITIVE LOGITS
     Neutral
    0.06
    ëħ
    0.06
     haven
    0.06
     SHIPPING
    0.06
    IBC
    0.06
    ANGO
    0.05
     neutral
    0.05
    ReadStream
    0.05
    EDI
    0.05
     neutrality
    0.05
    Activations Density 0.003%

    No Known Activations