© 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. 5-LLAMASCOPE-RES-131K
    11. 126031
    Prev
    Next
    INDEX
    Explanations

    acronyms and numbers related to identification and tax purposes

    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
    ToFit
    -0.07
    ivet
    -0.07
    à¥įयव
    -0.07
    UTERS
    -0.07
    Instrument
    -0.06
    ализи
    -0.06
    bero
    -0.06
    _MSB
    -0.06
    ẫ
    -0.06
    conto
    -0.06
    POSITIVE LOGITS
    lookup
    0.06
    les
    0.06
    à¸±à¸Ľ
    0.06
    eru
    0.06
     Burr
    0.06
    acker
    0.06
    uger
    0.06
     Palmer
    0.06
    uy
    0.06
    anda
    0.06
    Activations Density 0.001%

    No Known Activations