© 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. 129109
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
    PLICATE
    -0.06
     tomorrow
    -0.06
    ยา
    -0.06
    znik
    -0.06
    ResourceManager
    -0.06
     henne
    -0.06
    ocard
    -0.06
    emplates
    -0.06
    .DialogResult
    -0.06
    éré
    -0.06
    POSITIVE LOGITS
    usk
    0.06
     permissions
    0.06
     ModelState
    0.06
     ÎľÎ¿Î½
    0.06
    .ManyToMany
    0.06
    æŁ»
    0.06
     Milf
    0.05
     material
    0.05
    lek
    0.05
     indexer
    0.05
    Activations Density 0.010%

    No Known Activations