© 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. 40555
    Prev
    Next
    INDEX
    Explanations

    detailed statistical and factual information related to events and reports

    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
    次
    -0.06
    ä¸Ī
    -0.06
    639
    -0.06
    ako
    -0.06
     liken
    -0.06
     Stap
    -0.05
    ů
    -0.05
    chw
    -0.05
     facebook
    -0.05
     vag
    -0.05
    POSITIVE LOGITS
    isy
    0.08
    rint
    0.07
    upal
    0.07
     éĸ
    0.07
    pagination
    0.07
     indu
    0.07
     gec
    0.07
    ibase
    0.07
    .onViewCreated
    0.07
    indrome
    0.07
    Activations Density 0.021%

    No Known Activations