© 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. 117719
    Prev
    Next
    INDEX
    Explanations

    numerical quantifications and dimensions in a technical or scientific context

    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
    ãĥĥãĤ¯
    -0.07
    lÃŃn
    -0.07
    éĺħ读次æķ°
    -0.07
    onnement
    -0.07
     preferredStyle
    -0.07
    lisi
    -0.07
    erap
    -0.07
    rego
    -0.06
    efon
    -0.06
    ünchen
    -0.06
    POSITIVE LOGITS
    å·¦åı³
    0.08
    -strong
    0.07
    缮ãģ®
    0.07
    ìĶ©
    0.07
    ltk
    0.06
    uitka
    0.06
    以ä¸Ĭ
    0.06
    wen
    0.06
    hz
    0.06
    itos
    0.06
    Activations Density 0.003%

    No Known Activations