© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84054
    Prev
    Next
    INDEX
    Explanations

    dishes that highlight seafood and salads in a dining 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
    acting
    -0.07
     acting
    -0.07
     aftermarket
    -0.07
    istrovstvÃŃ
    -0.07
    .googleapis
    -0.07
     marsh
    -0.07
     GOODMAN
    -0.06
    ConnectionFactory
    -0.06
    é²ľ
    -0.06
    brands
    -0.06
    POSITIVE LOGITS
     specials
    0.09
     seasonal
    0.07
     menu
    0.07
    rotation
    0.07
     MenuItem
    0.07
     Banc
    0.06
    Signature
    0.06
    Benchmark
    0.06
    ứ
    0.06
    pat
    0.06
    Activations Density 0.034%

    No Known Activations