© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 58694
    Prev
    Next
    INDEX
    Explanations

    numerical codes or identifiers related to data entries

    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
    aan
    -0.07
    à¤Ĺल
    -0.07
    elage
    -0.06
    ruption
    -0.06
    μει
    -0.06
    ptal
    -0.06
    BuilderFactory
    -0.06
    irth
    -0.06
     Stanley
    -0.06
    udge
    -0.06
    POSITIVE LOGITS
    ocab
    0.08
    avir
    0.06
    بÙĩ
    0.06
     Rak
    0.06
     Lawson
    0.06
    ÙĪدÙĩ
    0.06
    eds
    0.06
     Moy
    0.06
     Cabin
    0.06
    orts
    0.06
    Activations Density 0.009%

    No Known Activations