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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28882
    Prev
    Next
    INDEX
    Explanations

    concepts related to significant changes or challenges

    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
    áº
    -0.07
    aldo
    -0.07
    ẻ
    -0.07
     вов
    -0.07
    iggins
    -0.07
    aniu
    -0.07
    apolis
    -0.07
    culus
    -0.07
    kv
    -0.07
    ouve
    -0.07
    POSITIVE LOGITS
     for
    0.07
     proverb
    0.07
     with
    0.06
    NewProp
    0.06
     on
    0.06
    HeaderCode
    0.06
     of
    0.05
    411
    0.05
    ä¸Ģæł·
    0.05
    mpp
    0.05
    Activations Density 0.043%

    No Known Activations