© 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. 57001
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups involved in a situation or context

    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
    ifter
    -0.06
    12
    -0.06
     rear
    -0.06
    1
    -0.06
    416
    -0.06
    ongyang
    -0.06
    ulas
    -0.06
    /Open
    -0.06
    304
    -0.06
    unt
    -0.06
    POSITIVE LOGITS
    egot
    0.08
    ëĭ´
    0.07
    вÑģÑı
    0.07
    δή
    0.07
    ëĭī
    0.06
    eker
    0.06
    anje
    0.06
    aida
    0.06
    .intellij
    0.06
    wu
    0.06
    Activations Density 0.000%

    No Known Activations