© 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. 90321
    Prev
    Next
    INDEX
    Explanations

    references to raffles and related prize drawing events

    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
    _SHARED
    -0.07
    جد
    -0.07
     accordion
    -0.06
    é«ĺæ¸ħ
    -0.06
    innen
    -0.06
    ossier
    -0.06
    è´Ł
    -0.06
    UDGE
    -0.06
    uso
    -0.06
    airs
    -0.06
    POSITIVE LOGITS
    дж
    0.08
    -winning
    0.07
    esome
    0.07
     Hazard
    0.07
    mitt
    0.07
    uci
    0.06
     ApiController
    0.06
    Ñħи
    0.06
    uten
    0.06
    rence
    0.06
    Activations Density 0.005%

    No Known Activations