© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60505
    Prev
    Next
    INDEX
    Explanations

    sensory details related to sounds and noises in various environments

    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
    andel
    -0.07
    ibar
    -0.06
    rage
    -0.06
    inue
    -0.06
     hugs
    -0.06
     condu
    -0.06
    conj
    -0.06
    ãĥ³ãĤ¯
    -0.06
    izu
    -0.06
    rech
    -0.06
    POSITIVE LOGITS
     sounded
    0.08
     sound
    0.07
     crunch
    0.07
    Sounds
    0.07
    562
    0.07
     crack
    0.07
    社
    0.07
     metallic
    0.06
     footsteps
    0.06
     sounds
    0.06
    Activations Density 0.051%

    No Known Activations