© 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. 15-LLAMASCOPE-RES-131K
    11. 61995
    Prev
    Next
    INDEX
    Explanations

    terms related to audio processing and signal management

    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
    ampil
    -0.07
    uve
    -0.07
    bart
    -0.07
    .serializer
    -0.07
    /stretch
    -0.06
    /power
    -0.06
    éļľ
    -0.06
    emap
    -0.06
    emodel
    -0.06
    бо
    -0.06
    POSITIVE LOGITS
    mers
    0.07
    -specific
    0.06
    éĸĵ
    0.06
    edia
    0.06
    -level
    0.06
    -Level
    0.06
    afa
    0.06
    sWith
    0.05
    amer
    0.05
    acher
    0.05
    Activations Density 0.038%

    No Known Activations