© 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. 117925
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to audio and signal processing

    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
    ysz
    -0.09
    arend
    -0.07
    ниÑĩ
    -0.07
    á»į
    -0.06
    Ú¯ÙĪ
    -0.06
    Flow
    -0.06
    ãĥ³ãĤ°
    -0.06
     Oaks
    -0.06
     æ´
    -0.06
    -CN
    -0.06
    POSITIVE LOGITS
     portion
    0.10
     portions
    0.10
     aspects
    0.10
     part
    0.09
     của
    0.08
     aspect
    0.08
     of
    0.08
    portion
    0.08
    éĥ¨åĪĨ
    0.07
     (?)
    0.07
    Activations Density 0.075%

    No Known Activations