© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56587
    Prev
    Next
    INDEX
    Explanations

    references to identifying or locating sources or origins of sounds or situations

    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
    esch
    -0.07
     Lager
    -0.06
     Lag
    -0.06
    ÙĪص
    -0.06
     Damen
    -0.06
    ucc
    -0.06
    avage
    -0.06
    636
    -0.06
    bury
    -0.05
    redirectTo
    -0.05
    POSITIVE LOGITS
     source
    0.17
     sources
    0.15
    source
    0.15
     Source
    0.14
    -source
    0.13
    sources
    0.13
     SOURCE
    0.13
     иÑģÑĤоÑĩ
    0.13
    æºIJ
    0.13
    .source
    0.12
    Activations Density 0.076%

    No Known Activations