© 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. 86308
    Prev
    Next
    INDEX
    Explanations

    non-specific formatting elements or markers within the text

    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
    enberg
    -0.07
    ombo
    -0.07
    shaw
    -0.07
    ajes
    -0.06
    raph
    -0.06
    út
    -0.06
    άνι
    -0.06
    AGER
    -0.06
    agger
    -0.06
    813
    -0.06
    POSITIVE LOGITS
    chl
    0.07
    odyn
    0.06
    ån
    0.06
    ТÐŀ
    0.06
    okens
    0.06
    noinspection
    0.06
    inic
    0.06
    émon
    0.06
     Vel
    0.06
    unday
    0.06
    Activations Density 0.002%

    No Known Activations