© 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. 3436
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and scores

    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
    imar
    -0.08
    dit
    -0.08
    acemark
    -0.08
    ATAR
    -0.08
    tiv
    -0.08
    bote
    -0.07
    356
    -0.07
    EncodingException
    -0.07
    prak
    -0.07
    \ORM
    -0.07
    POSITIVE LOGITS
     Service
    0.06
    Ñİк
    0.06
     fluct
    0.06
     capital
    0.06
     Cum
    0.05
     Hus
    0.05
     Joshua
    0.05
    umb
    0.05
     ex
    0.05
     Miss
    0.05
    Activations Density 0.001%

    No Known Activations