© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97996
    Prev
    Next
    INDEX
    Explanations

    referential words and phrases indicating specific topics or subjects within discussions

    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
    ammer
    -0.07
    ania
    -0.07
    oko
    -0.07
     sert
    -0.07
    λÏī
    -0.07
    atsu
    -0.07
    avers
    -0.07
    ानव
    -0.07
    ürn
    -0.07
    eko
    -0.07
    POSITIVE LOGITS
    pec
    0.07
    .xtext
    0.06
    xe
    0.06
    eron
    0.06
    cke
    0.06
    soever
    0.06
     Estates
    0.05
     kancel
    0.05
    çļ
    0.05
    ©
    0.05
    Activations Density 0.000%

    No Known Activations