© 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. 15-LLAMASCOPE-RES-131K
    11. 104407
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical structures and properties

    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
    ombo
    -0.09
    ossal
    -0.08
    legg
    -0.07
    chner
    -0.07
    .sul
    -0.07
    affer
    -0.07
    	Copyright
    -0.07
    ÏĨÏīν
    -0.07
    asca
    -0.07
    (disposing
    -0.07
    POSITIVE LOGITS
    548
    0.06
    emas
    0.06
    /stdc
    0.06
    {{--
    0.06
    yon
    0.06
    451
    0.06
    mons
    0.06
    259
    0.05
    ibe
    0.05
    739
    0.05
    Activations Density 0.016%

    No Known Activations