© 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. 60739
    Prev
    Next
    INDEX
    Explanations

    concepts related to relationships and connections

    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
    одо
    -0.07
    ermen
    -0.07
    .yahoo
    -0.07
    SFML
    -0.07
    bih
    -0.07
    erk
    -0.06
    à¹īาà¸ĩ
    -0.06
     transform
    -0.06
    alin
    -0.06
    ÑĦеÑĢ
    -0.06
    POSITIVE LOGITS
     constituents
    0.07
    Ordinal
    0.07
    _hierarchy
    0.07
    inness
    0.07
    cae
    0.06
     Burgess
    0.06
    umb
    0.06
    oÄŁ
    0.06
    759
    0.06
    hape
    0.06
    Activations Density 0.030%

    No Known Activations