© 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. 105714
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that suggest depth or complexity

    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
    ei
    -0.06
     gran
    -0.06
    857
    -0.06
     бак
    -0.05
    SF
    -0.05
    anie
    -0.05
    umber
    -0.05
    ãĥ¼ãĤ¿ãĥ¼
    -0.05
    FILES
    -0.05
    ^^
    -0.05
    POSITIVE LOGITS
    utr
    0.07
     ê°Ŀ
    0.07
     pick
    0.07
    olls
    0.07
    VERR
    0.07
    igon
    0.07
    κÏĮ
    0.07
     ekip
    0.07
    ledon
    0.07
     Gill
    0.06
    Activations Density 0.000%

    No Known Activations