© 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. 71659
    Prev
    Next
    INDEX
    Explanations

    key nouns and terms related to closure or finality

    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
    ema
    -0.06
    alytics
    -0.06
     Cav
    -0.06
    atives
    -0.06
    _Output
    -0.06
     Vaults
    -0.06
    uzu
    -0.06
     respective
    -0.05
    dsp
    -0.05
    éħ
    -0.05
    POSITIVE LOGITS
     -:-
    0.08
    avian
    0.07
    iny
    0.07
     Herr
    0.07
     ÏĦÏĮ
    0.06
    lah
    0.06
    .forName
    0.06
    оÑĤоÑĢ
    0.06
    еле
    0.06
    strip
    0.06
    Activations Density 0.000%

    No Known Activations