© 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. 61255
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptocurrency and its mechanisms

    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
    ebo
    -0.07
    ÙĪØ·
    -0.07
    edom
    -0.07
    rance
    -0.07
     Hem
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
     hem
    -0.06
    ither
    -0.06
     hemisphere
    -0.06
    BCM
    -0.06
    POSITIVE LOGITS
     adoption
    0.07
     escorte
    0.06
    รà¸Ńà¸ĩ
    0.06
     features
    0.06
     Layer
    0.06
     latency
    0.06
    jective
    0.06
    enna
    0.06
    ensus
    0.06
    _features
    0.06
    Activations Density 0.007%

    No Known Activations