© 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. 118539
    Prev
    Next
    INDEX
    Explanations

    references to organizations and initiatives related to adventure and ecological tourism

    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
     bonuses
    -0.06
    ÑģÑĮк
    -0.06
     Tonight
    -0.06
    allon
    -0.06
     incent
    -0.06
    olley
    -0.06
    Routine
    -0.06
    ÃŃž
    -0.06
    Tonight
    -0.05
     bonus
    -0.05
    POSITIVE LOGITS
    bucks
    0.07
     provoz
    0.07
    obil
    0.07
    ifacts
    0.07
     tiny
    0.07
     Paren
    0.07
    stered
    0.07
     Tiny
    0.07
    Tiny
    0.07
    avery
    0.07
    Activations Density 0.010%

    No Known Activations