© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    names and terms related to sports and entertainment

    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
    िष
    -0.06
    .âĢ¦
    -0.06
    ?↵
    -0.06
    ↵
    -0.06
    dr
    -0.06
    âĢ¦
    -0.05
    nam
    -0.05
     extremes
    -0.05
    z
    -0.05
    ↵↵
    -0.05
    POSITIVE LOGITS
    urette
    0.09
    Ñıб
    0.09
    inki
    0.08
    bidden
    0.08
    ://
    0.08
     zwar
    0.08
    :///
    0.08
    .EventType
    0.08
    orris
    0.07
    ADDE
    0.07
    Activations Density 0.043%

    No Known Activations