© 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. 76329
    Prev
    Next
    INDEX
    Explanations

    instances of fines and suspensions 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
    uhn
    -0.08
    ãĥ³ãĥĩ
    -0.07
     Prison
    -0.06
    çŃĴ
    -0.06
    okus
    -0.06
    eson
    -0.06
    acock
    -0.06
     prisoners
    -0.06
    ivé
    -0.06
     Exit
    -0.06
    POSITIVE LOGITS
     suspension
    0.12
     Suspension
    0.10
     susp
    0.09
     suspended
    0.09
     suspend
    0.09
     Appeals
    0.08
    Susp
    0.08
    suspend
    0.07
    rost
    0.07
    vais
    0.07
    Activations Density 0.014%

    No Known Activations