© 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. 103702
    Prev
    Next
    INDEX
    Explanations

    technical terms related to chemical processes and reactions

    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
    \grid
    -0.07
    554
    -0.06
     Siege
    -0.06
    lename
    -0.06
    coil
    -0.06
     Daisy
    -0.06
    çł²
    -0.06
     Scar
    -0.06
     Eisen
    -0.06
    /backend
    -0.06
    POSITIVE LOGITS
     flight
    0.09
    ircraft
    0.08
     crew
    0.07
    ëĤł
    0.07
     Flight
    0.07
     BUFF
    0.07
    座
    0.07
     taxing
    0.07
     cabin
    0.07
     aircraft
    0.07
    Activations Density 0.021%

    No Known Activations