© 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. 61706
    Prev
    Next
    INDEX
    Explanations

    elements related to questions and inquiries

    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
    Ñıг
    -0.08
    央
    -0.08
    -addons
    -0.08
    antity
    -0.08
    лоÑĤ
    -0.07
    åĩ½
    -0.07
    cret
    -0.07
    UFFER
    -0.07
    antom
    -0.07
    erse
    -0.07
    POSITIVE LOGITS
     Dr
    0.06
    achi
    0.06
    PCS
    0.06
    _Util
    0.06
     -
    0.06
    iblings
    0.06
    orus
    0.05
     chairman
    0.05
     util
    0.05
     erection
    0.05
    Activations Density 0.015%

    No Known Activations