Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5157
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to audio and speaker performance

    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
     Vision
    -0.06
    /
    -0.06
    (
    -0.06
    -
    -0.06
     absorbing
    -0.06
    "
    -0.06
    [
    -0.05
    op
    -0.05
    x
    -0.05
    ag
    -0.05
    POSITIVE LOGITS
    .pitch
    0.13
    zcze
    0.12
     pitch
    0.11
    Pitch
    0.11
     Pitch
    0.11
     vowel
    0.10
     speech
    0.10
    pitch
    0.10
    speech
    0.10
     voiced
    0.10
    Activations Density 0.088%

    No Known Activations