© 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. 90408
    Prev
    Next
    INDEX
    Explanations

    elements related to outdoor activities and environments

    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
    639
    -0.07
    541
    -0.06
     foss
    -0.05
     Fal
    -0.05
    æ¹
    -0.05
    umu
    -0.05
     counter
    -0.05
    %B
    -0.05
    ³
    -0.05
     multip
    -0.05
    POSITIVE LOGITS
    meld
    0.08
    åľĪ
    0.07
    coon
    0.07
    енка
    0.07
    .BLL
    0.07
    clair
    0.07
    rede
    0.07
    cel
    0.07
    èĪį
    0.07
    Teams
    0.07
    Activations Density 0.001%

    No Known Activations