© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating distances or lengths related to actions in sports

    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
    legg
    -0.08
    erot
    -0.07
    unami
    -0.07
    ndl
    -0.07
    ocity
    -0.06
    soles
    -0.06
    acades
    -0.06
    ottes
    -0.06
    skirts
    -0.06
     ë°ĶëŀįëĭĪëĭ¤
    -0.06
    POSITIVE LOGITS
     Bookmark
    0.07
    ylene
    0.07
    usto
    0.07
    Toy
    0.06
    ÑĢеди
    0.06
     standpoint
    0.06
     scratch
    0.06
    곤
    0.06
     Scratch
    0.06
    _stand
    0.06
    Activations Density 0.005%

    No Known Activations