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

    Neuronpedia

    Jacobian LensNEW
    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. 128895
    Prev
    Next
    INDEX
    Explanations

    references to shared knowledge or common understanding

    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
    ลาย
    -0.07
    wick
    -0.07
    ë§ī
    -0.06
    _Tick
    -0.06
    Desk
    -0.06
    racak
    -0.06
    etting
    -0.06
     ãĥ¯
    -0.06
    idal
    -0.06
    ssi
    -0.06
    POSITIVE LOGITS
     know
    0.15
     known
    0.13
     knows
    0.13
    known
    0.12
     Know
    0.12
    çŁ¥
    0.10
    -known
    0.10
     çŁ¥
    0.10
    Know
    0.10
    know
    0.10
    Activations Density 0.080%

    No Known Activations