© 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. 75296
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numerical values related to dates or counts

    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
    izarre
    -0.06
     Cov
    -0.06
    DN
    -0.05
     Cunningham
    -0.05
     Barn
    -0.05
    pez
    -0.05
    ledo
    -0.05
    plitude
    -0.05
    ë·
    -0.05
     sens
    -0.05
    POSITIVE LOGITS
    /chart
    0.07
    orea
    0.07
    /cms
    0.07
     ============================================================================↵
    0.06
    oidal
    0.06
    ãĥ«ãĥķ
    0.06
     çī
    0.06
    utut
    0.06
    _USED
    0.06
    -valu
    0.06
    Activations Density 0.007%

    No Known Activations