© 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. 130124
    Prev
    Next
    INDEX
    Explanations

    sections and references related to educational content and language instruction

    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
    èĭ±è¯Ń
    -0.13
     Languages
    -0.12
     languages
    -0.12
    èĭ±æĸĩ
    -0.11
     English
    -0.11
     ìĺģìĸ´
    -0.11
    èĭ±èªŀ
    -0.10
     english
    -0.10
    Languages
    -0.10
     Ä°ngilizce
    -0.10
    POSITIVE LOGITS
     Artem
    0.06
    ugen
    0.06
    ulin
    0.06
     Imper
    0.06
     â
    0.05
     clit
    0.05
    ety
    0.05
    OUSE
    0.05
    stem
    0.05
     Eisen
    0.05
    Activations Density 0.027%

    No Known Activations