© 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. 9-LLAMASCOPE-RES-131K
    11. 95874
    Prev
    Next
    INDEX
    Explanations

    references to audiobooks and legal professions

    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
    orum
    -0.07
    trand
    -0.06
     enf
    -0.06
    ãģĤ
    -0.06
    achs
    -0.06
     Infer
    -0.06
    éĩİ
    -0.06
    绣
    -0.06
    anela
    -0.05
    UBLISH
    -0.05
    POSITIVE LOGITS
    gnu
    0.07
    è´Ł
    0.07
    ernen
    0.07
    è²ł
    0.07
    ếp
    0.07
    ÙĪدÙĩ
    0.07
    Squared
    0.06
    ãĥ³ãĥĩãĤ£
    0.06
    _INCLUDED
    0.06
     neust
    0.06
    Activations Density 0.000%

    No Known Activations