© 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. 129041
    Prev
    Next
    INDEX
    Explanations

    references to injuries in athletes

    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
     Ekon
    -0.06
    ference
    -0.06
    veau
    -0.06
    rift
    -0.06
    죽
    -0.06
     Plasma
    -0.06
    rita
    -0.06
     powering
    -0.05
    hta
    -0.05
    .nodeType
    -0.05
    POSITIVE LOGITS
     injury
    0.21
     injuries
    0.19
     Injury
    0.19
     injured
    0.18
    juries
    0.13
     injuring
    0.13
    jured
    0.11
    伤
    0.11
    jury
    0.11
     inj
    0.10
    Activations Density 0.233%

    No Known Activations