© 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. 103196
    Prev
    Next
    INDEX
    Explanations

    financial terms or data relevant to calculations

    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
    à¸ĺรรม
    -0.07
     Muss
    -0.07
     Ñıке
    -0.07
    hist
    -0.07
    ahren
    -0.06
    .AutoScaleMode
    -0.06
    thalm
    -0.06
     Ages
    -0.06
    aign
    -0.06
    åĺĽ
    -0.06
    POSITIVE LOGITS
     our
    0.07
     respective
    0.06
    346
    0.06
    quot
    0.06
     this
    0.06
    381
    0.06
     Categories
    0.06
    .lst
    0.06
    azers
    0.06
    endo
    0.06
    Activations Density 0.027%

    No Known Activations