© 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. 15-LLAMASCOPE-RES-131K
    11. 26800
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics related to statistics and performance

    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
    orent
    -0.07
     Kür
    -0.07
     lesb
    -0.07
    æĹ
    -0.07
    ordinate
    -0.07
    .parameters
    -0.06
    аÑĤе
    -0.06
     Anth
    -0.06
     Essex
    -0.06
    oldt
    -0.06
    POSITIVE LOGITS
     threshold
    0.06
    .goal
    0.06
    cratch
    0.06
     Threshold
    0.06
    _PROVIDER
    0.06
    ihan
    0.06
    otts
    0.06
    aits
    0.06
    á»Ĺ
    0.06
     Canonical
    0.06
    Activations Density 0.011%

    No Known Activations