© 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. 15-LLAMASCOPE-RES-131K
    11. 61721
    Prev
    Next
    INDEX
    Explanations

    expressions related to performance and consistency in sports

    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
     Weiner
    -0.08
     tol
    -0.07
    jÃŃm
    -0.07
    нÑĸв
    -0.07
    olson
    -0.07
    _mux
    -0.07
    _MUX
    -0.06
    abis
    -0.06
    utes
    -0.06
    TabPage
    -0.06
    POSITIVE LOGITS
     lately
    0.09
    iglia
    0.06
    outil
    0.06
    elier
    0.06
    ÑģÑĤÑĮ
    0.06
    {@
    0.06
    heading
    0.05
    tu
    0.05
    åij³
    0.05
    ernet
    0.05
    Activations Density 0.012%

    No Known Activations