© 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. 71424
    Prev
    Next
    INDEX
    Explanations

    inquiries about travel-related logistics and accommodations

    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
    ombat
    -0.07
     De
    -0.07
    è©
    -0.06
    ngx
    -0.06
    (çģ«
    -0.06
    703
    -0.06
     Fiction
    -0.06
    engin
    -0.06
     cis
    -0.06
     opráv
    -0.06
    POSITIVE LOGITS
    oen
    0.07
     addCriterion
    0.06
    404
    0.06
    ASA
    0.06
    çľ
    0.06
    ouri
    0.06
    /animate
    0.06
    ×ķ
    0.06
     fractional
    0.06
    emem
    0.06
    Activations Density 0.015%

    No Known Activations