© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127222
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to significant places or concepts

    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
    ráž
    -0.07
    iral
    -0.07
    edin
    -0.07
    ebek
    -0.07
    xcf
    -0.07
    edback
    -0.07
    ecd
    -0.07
     ÑģобоÑİ
    -0.07
    sto
    -0.07
    ÙĨدÙĩ
    -0.07
    POSITIVE LOGITS
    _compat
    0.07
    oken
    0.07
    /on
    0.06
    heit
    0.06
    abbix
    0.06
    eous
    0.06
    _PIX
    0.06
    ear
    0.06
    ickle
    0.06
    reeze
    0.06
    Activations Density 0.082%

    No Known Activations