© 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. 998
    Prev
    Next
    INDEX
    Explanations

    newline characters in the text

    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
    SSIP
    -0.08
    growth
    -0.07
    gas
    -0.07
    oj
    -0.07
    gio
    -0.07
    olumn
    -0.07
    crop
    -0.07
    gis
    -0.07
     crop
    -0.06
    -ÑĤо
    -0.06
    POSITIVE LOGITS
    olta
    0.07
    setError
    0.07
    itional
    0.07
    urma
    0.06
    swer
    0.06
    ullo
    0.06
    ecz
    0.06
    achts
    0.06
    iswa
    0.06
    embro
    0.06
    Activations Density 0.007%

    No Known Activations