© 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. 17-LLAMASCOPE-RES-131K
    11. 95842
    Prev
    Next
    INDEX
    Explanations

    references to specific qualities, characteristics, or features

    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
    esc
    -0.07
    okit
    -0.07
    аÑİ
    -0.07
    inel
    -0.07
    ов
    -0.07
    endas
    -0.07
    aret
    -0.07
    PACK
    -0.07
    اء
    -0.07
    .parallel
    -0.07
    POSITIVE LOGITS
    ily
    0.15
    ity
    0.14
    ities
    0.14
    mente
    0.11
    istic
    0.10
    ized
    0.09
    ty
    0.09
    istically
    0.09
    idades
    0.09
    ités
    0.09
    Activations Density 0.019%

    No Known Activations