© 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. 71517
    Prev
    Next
    INDEX
    Explanations

    numeric expressions related to dimensions or measurements

    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
    ogo
    -0.06
     holders
    -0.06
    inho
    -0.06
    ear
    -0.05
    Gap
    -0.05
     course
    -0.05
    ETA
    -0.05
     overdue
    -0.05
    andas
    -0.05
    olina
    -0.05
    POSITIVE LOGITS
     bay
    0.08
    ä¸Ī
    0.08
    bay
    0.07
     кÑĥÑħ
    0.07
    ynamo
    0.07
    ãĤ¡
    0.07
    ÑĢÑĥкÑĤ
    0.07
    asz
    0.07
    IEnumerator
    0.07
     zel
    0.07
    Activations Density 0.000%

    No Known Activations