© 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. 76206
    Prev
    Next
    INDEX
    Explanations

    quantitative references, particularly numbers and counts

    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
    erece
    -0.08
    ietet
    -0.08
     maduras
    -0.07
    üssen
    -0.07
    ansk
    -0.07
    ogne
    -0.07
    ÐĴÑĤ
    -0.07
    itat
    -0.07
    omp
    -0.07
    ìĹ´
    -0.07
    POSITIVE LOGITS
     years
    0.07
    oland
    0.07
    ola
    0.07
     stint
    0.06
    +
    0.06
     Hatch
    0.06
     miscon
    0.06
     pr
    0.06
    ed
    0.06
     year
    0.06
    Activations Density 0.018%

    No Known Activations