© 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 EvalsExportsinterp-engineNEWAPI 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. 105405
    Prev
    Next
    INDEX
    Explanations

    key concepts and arguments related to reasoning and problem-solving

    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
    opoulos
    -0.08
    fy
    -0.07
    stroy
    -0.07
    isos
    -0.07
    EV
    -0.06
    |=↵
    -0.06
    shan
    -0.06
    άνι
    -0.06
    ìĸ´ëĤĺ
    -0.06
    amer
    -0.06
    POSITIVE LOGITS
    INGLE
    0.07
    ukkan
    0.06
    972
    0.06
     jich
    0.06
    ÐĺТ
    0.06
    theid
    0.06
    (er
    0.06
    _TOO
    0.06
     ims
    0.06
    æ¹
    0.06
    Activations Density 0.044%

    No Known Activations