© 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. 9-LLAMASCOPE-RES-131K
    11. 95587
    Prev
    Next
    INDEX
    Explanations

    references to box office performance in films

    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
     mod
    -0.06
    lich
    -0.06
    zent
    -0.06
    zell
    -0.06
    aries
    -0.06
     Moo
    -0.06
    sehen
    -0.06
    aint
    -0.06
     compact
    -0.06
     Nations
    -0.05
    POSITIVE LOGITS
    boru
    0.07
     latter
    0.07
    manship
    0.07
    .Persistent
    0.07
    .getIn
    0.06
    ABL
    0.06
    .paper
    0.06
    ypi
    0.06
    .XR
    0.06
    apia
    0.06
    Activations Density 0.002%

    No Known Activations