© 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. 118599
    Prev
    Next
    INDEX
    Explanations

    references to specific historical racing models and 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
     currently
    -0.07
     hasn
    -0.07
     mechanic
    -0.07
    UPPORT
    -0.07
    ContentAlignment
    -0.07
    EXPECT
    -0.06
    .native
    -0.06
     haven
    -0.06
     Sür
    -0.06
    βα
    -0.06
    POSITIVE LOGITS
    awe
    0.07
    ICES
    0.07
     IPT
    0.06
    -layout
    0.06
    |%
    0.06
    chant
    0.06
    :CGRect
    0.06
    ipl
    0.06
     Vide
    0.06
    essler
    0.06
    Activations Density 0.003%

    No Known Activations