© 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 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. 40470
    Prev
    Next
    INDEX
    Explanations

    terms related to audio signal processing and calibration

    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
     -
    -0.08
     –
    -0.07
    -
    -0.07
     (
    -0.06
     let
    -0.06
     this
    -0.06
     —
    -0.06
    egg
    -0.06
     where
    -0.06
     “
    -0.06
    POSITIVE LOGITS
    oplayer
    0.08
    ãĤ£
    0.08
     ÐĶеÑĢжав
    0.08
    йн
    0.08
    æĨ¶
    0.07
    allis
    0.07
    oogle
    0.07
    èĩ³å°ij
    0.07
    znik
    0.07
    ãĥ¥
    0.07
    Activations Density 0.079%

    No Known Activations