© 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. 130160
    Prev
    Next
    INDEX
    Explanations

    phrases that describe variations or distinctions

    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
    pei
    -0.07
    udu
    -0.06
    cae
    -0.06
    rysler
    -0.06
    ersen
    -0.06
    íĸī
    -0.05
     compatible
    -0.05
    ANS
    -0.05
    ryo
    -0.05
     Advice
    -0.05
    POSITIVE LOGITS
     unusual
    0.10
    usual
    0.10
     usual
    0.09
     uniqueness
    0.09
    ypical
    0.08
     compared
    0.08
    unexpected
    0.08
     unique
    0.08
    unique
    0.08
    ãĥ¼ãĤ¯
    0.07
    Activations Density 0.025%

    No Known Activations