© 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. 97665
    Prev
    Next
    INDEX
    Explanations

    instances of frequency and repetition in statements or references

    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
    OfSize
    -0.07
    nech
    -0.07
    arring
    -0.07
    обÑĭ
    -0.07
    loub
    -0.07
    hu
    -0.07
    aec
    -0.07
    orro
    -0.06
    ÑĢоÑģÑĤо
    -0.06
    nection
    -0.06
    POSITIVE LOGITS
    :disable
    0.06
    writeln
    0.06
     lately
    0.06
    .struts
    0.06
     his
    0.06
    elper
    0.06
    sburgh
    0.06
    继
    0.06
    dig
    0.06
    ftp
    0.05
    Activations Density 0.052%

    No Known Activations