© 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. 16116
    Prev
    Next
    INDEX
    Explanations

    instances of meetings and conferences

    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
    owl
    -0.07
    ozor
    -0.07
    onen
    -0.07
    iyon
    -0.07
    tember
    -0.07
    /ec
    -0.06
    /fr
    -0.06
    .Sum
    -0.06
    lij
    -0.06
    æķij
    -0.06
    POSITIVE LOGITS
     conducted
    0.09
     session
    0.09
     sessions
    0.08
     held
    0.07
     productive
    0.07
    =session
    0.07
     appointment
    0.07
    held
    0.07
     sesso
    0.07
     appointments
    0.07
    Activations Density 0.028%

    No Known Activations