© 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. 78680
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "nothing"

    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
     reserves
    -0.07
    dig
    -0.06
    igu
    -0.06
    929
    -0.06
    amik
    -0.06
     Hass
    -0.05
    avra
    -0.05
    -0.05
    ansk
    -0.05
    sure
    -0.05
    POSITIVE LOGITS
    ónico
    0.08
    oling
    0.07
     wrong
    0.07
    IGHL
    0.07
    urat
    0.07
    angstrom
    0.07
    icari
    0.07
    ÏĦεÏĤ
    0.07
     else
    0.06
     anim
    0.06
    Activations Density 0.009%

    No Known Activations