© 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. 61735
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols commonly used in digital formats and coding

    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
    alnız
    -0.06
     Roose
    -0.06
    subtype
    -0.06
    ison
    -0.06
     Attribution
    -0.06
    /or
    -0.06
    г
    -0.06
    525
    -0.06
     corps
    -0.06
     Economist
    -0.06
    POSITIVE LOGITS
    illard
    0.10
    ï¸
    0.09
    ï¸ı
    0.08
    emmel
    0.07
    ìļ±
    0.07
    iley
    0.07
    zeug
    0.07
    stant
    0.07
    nant
    0.07
    lein
    0.07
    Activations Density 0.003%

    No Known Activations