© 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. 40640
    Prev
    Next
    INDEX
    Explanations

    technical jargon and numerical data related to sound technology and acoustic methods

    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
     fas
    -0.07
    .NewLine
    -0.07
    estre
    -0.07
    istes
    -0.07
    sob
    -0.06
    sher
    -0.06
    asin
    -0.06
    /problems
    -0.06
    lesia
    -0.06
    oucher
    -0.06
    POSITIVE LOGITS
    49
    0.07
    59
    0.06
    56
    0.06
    46
    0.06
    54
    0.06
    ichi
    0.06
    51
    0.06
    ogy
    0.06
     ÑĤек
    0.06
     Forces
    0.06
    Activations Density 0.048%

    No Known Activations