© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71364
    Prev
    Next
    INDEX
    Explanations

    phrases related to team performance and dynamics

    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
     Weiner
    -0.08
    ustos
    -0.07
    ickers
    -0.07
    æ¦
    -0.07
     tol
    -0.07
    inkle
    -0.06
    нÑĸв
    -0.06
    eward
    -0.06
    ationally
    -0.06
    utm
    -0.06
    POSITIVE LOGITS
     lately
    0.10
     recently
    0.07
     recent
    0.06
    iglia
    0.06
    RelativeTo
    0.06
     relative
    0.06
     late
    0.06
    end
    0.06
    outil
    0.06
     enough
    0.06
    Activations Density 0.012%

    No Known Activations