© 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. 129209
    Prev
    Next
    INDEX
    Explanations

    detailed evaluations of athlete performance and contracts

    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
    .scalablytyped
    -0.07
    è¯Ŀ
    -0.07
    ufe
    -0.06
    sworth
    -0.06
     lesson
    -0.06
     Shank
    -0.06
    onus
    -0.06
     dáv
    -0.06
    _unused
    -0.06
     frustrations
    -0.06
    POSITIVE LOGITS
    æľīéĻIJ
    0.08
    µ
    0.07
     limited
    0.07
    bersome
    0.07
    ahren
    0.07
    limited
    0.07
    ojis
    0.07
     only
    0.07
     decl
    0.07
    GRAY
    0.07
    Activations Density 0.042%

    No Known Activations