© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15805
    Prev
    Next
    INDEX
    Explanations

    numeric measurements and dimensions

    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
    олож
    -0.06
    eve
    -0.06
    oven
    -0.06
     bol
    -0.06
    clud
    -0.06
    èĻŁ
    -0.06
    ledon
    -0.06
    ocre
    -0.06
    Äįe
    -0.06
    ajes
    -0.06
    POSITIVE LOGITS
    uitka
    0.07
    пÑĢиклад
    0.07
    ãĤħ
    0.07
    ÑĢож
    0.06
    .databinding
    0.06
    tvrt
    0.06
    arella
    0.06
    ulace
    0.06
    ¯
    0.06
     kÃŃch
    0.06
    Activations Density 0.004%

    No Known Activations