© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82142
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and environmental science

    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
    _Native
    -0.08
    iris
    -0.07
     integrity
    -0.07
    thag
    -0.07
     Integrity
    -0.06
    onis
    -0.06
     éĩİ
    -0.06
    RET
    -0.06
     bleeding
    -0.06
    odzi
    -0.06
    POSITIVE LOGITS
     microscopic
    0.08
     Blind
    0.07
     Hairst
    0.07
     Antarctic
    0.07
    lice
    0.06
     Tube
    0.06
     nem
    0.06
     fil
    0.06
     worker
    0.06
    Æ¡
    0.06
    Activations Density 0.009%

    No Known Activations