© 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. 87711
    Prev
    Next
    INDEX
    Explanations

    ways to express methods or strategies

    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
    imits
    -0.07
    ç¤
    -0.07
    áo
    -0.07
     amongst
    -0.07
    aney
    -0.06
    ilor
    -0.06
    kas
    -0.06
    sey
    -0.06
    KeyEvent
    -0.06
    sville
    -0.06
    POSITIVE LOGITS
     to
    0.07
    ÑĢаж
    0.06
    ADF
    0.06
     Tw
    0.06
     way
    0.06
    herits
    0.06
    544
    0.06
    regor
    0.06
     Rounds
    0.06
    aug
    0.06
    Activations Density 0.010%

    No Known Activations