© 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. 27112
    Prev
    Next
    INDEX
    Explanations

    terms related to sound and its various representations and interactions

    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
    ebin
    -0.07
    oval
    -0.07
    eger
    -0.07
    acin
    -0.07
    eri
    -0.07
    yor
    -0.07
    plat
    -0.07
    imet
    -0.07
    ector
    -0.07
    Chain
    -0.06
    POSITIVE LOGITS
     exec
    0.07
    FF
    0.06
    дÑĭ
    0.06
    056
    0.06
    412
    0.06
    652
    0.06
    orc
    0.06
    Ñĸж
    0.06
    оÑĤа
    0.06
    ottes
    0.06
    Activations Density 0.052%

    No Known Activations