© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77589
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio and video signal quality

    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
    byname
    -0.07
    allen
    -0.07
    ckpt
    -0.07
    Sketch
    -0.07
    .xhtml
    -0.07
    @student
    -0.07
     piger
    -0.07
    ÎŃαÏĤ
    -0.07
    alem
    -0.06
    icaid
    -0.06
    POSITIVE LOGITS
    FW
    0.07
     edge
    0.06
     Edge
    0.06
     ISO
    0.06
    ltre
    0.06
     artifact
    0.06
    輪
    0.06
    street
    0.06
     test
    0.06
    FFF
    0.06
    Activations Density 0.000%

    No Known Activations