© 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. 125467
    Prev
    Next
    INDEX
    Explanations

    concepts related to digital signal processing and echo cancellation

    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
    CLU
    -0.07
     {{{
    -0.07
    جاÙħ
    -0.07
     akci
    -0.07
    idata
    -0.07
     é¹
    -0.07
    OV
    -0.07
    -liter
    -0.07
     duż
    -0.07
     strate
    -0.07
    POSITIVE LOGITS
    æŁĦ
    0.07
    owitz
    0.06
    ocol
    0.06
    inz
    0.06
     Till
    0.06
    ¤íĶĦ
    0.06
    ätz
    0.06
    thy
    0.06
    uten
    0.06
    ano
    0.06
    Activations Density 0.144%

    No Known Activations