© 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. 82195
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
    ured
    -0.08
    lsen
    -0.08
    jabi
    -0.08
    迹
    -0.07
     sebe
    -0.07
    urette
    -0.07
    >{!!
    -0.07
    ornings
    -0.07
    ghan
    -0.07
    olik
    -0.07
    POSITIVE LOGITS
    ottie
    0.07
    -century
    0.07
    ogonal
    0.07
    ousand
    0.06
    otted
    0.06
    si
    0.06
    Ķ
    0.06
    ÙĪاء
    0.06
    275
    0.06
    PTS
    0.06
    Activations Density 0.008%

    No Known Activations