© 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. 5-LLAMASCOPE-RES-131K
    11. 126075
    Prev
    Next
    INDEX
    Explanations

    terms related to coaching and coaching staff in sports contexts

    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
    lesia
    -0.08
    osl
    -0.08
    952
    -0.08
    thur
    -0.07
    strand
    -0.07
    ãĥ³ãĥĦ
    -0.07
    лиÑĨ
    -0.07
    ös
    -0.07
    Composer
    -0.07
     Kültür
    -0.07
    POSITIVE LOGITS
     Pel
    0.06
    0.06
     de
    0.06
    eron
    0.06
     pel
    0.06
    rians
    0.05
     dich
    0.05
     Lo
    0.05
     Bast
    0.05
     binary
    0.05
    Activations Density 0.009%

    No Known Activations