© 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. 41285
    Prev
    Next
    INDEX
    Explanations

    programming syntax or code structure

    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
    ÙĦاÙĦ
    -0.07
    pees
    -0.07
    лем
    -0.07
    boo
    -0.06
    oulos
    -0.06
    OUGH
    -0.06
    ÑģÑĭл
    -0.06
    LOOR
    -0.06
    idges
    -0.06
    елÑİ
    -0.06
    POSITIVE LOGITS
     similar
    0.07
    DEX
    0.06
    yne
    0.06
     Hollow
    0.06
    fld
    0.06
    ayne
    0.06
     Fax
    0.06
    .dylib
    0.06
    agal
    0.06
     nackte
    0.06
    Activations Density 0.003%

    No Known Activations