© 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. 106443
    Prev
    Next
    INDEX
    Explanations

    references to organizational leadership and positions

    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
    imensional
    -0.06
    olib
    -0.06
    anine
    -0.06
    Ñħо
    -0.06
    907
    -0.06
    ิà¹Ĥล
    -0.06
    450
    -0.05
    -describedby
    -0.05
    Sab
    -0.05
    451
    -0.05
    POSITIVE LOGITS
    -or
    0.07
    /drivers
    0.07
    orang
    0.07
    .BorderColor
    0.06
    .twig
    0.06
    unger
    0.06
    ãĥ³ãĤ°
    0.06
     diary
    0.06
     tripod
    0.06
    nement
    0.06
    Activations Density 0.066%

    No Known Activations