© 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. 124223
    Prev
    Next
    INDEX
    Explanations

    actions related to suggestions, recommendations, or considerations

    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
    Ä±ÅŁÄ±
    -0.07
     è®
    -0.07
    Ư
    -0.07
    rosse
    -0.07
     è«
    -0.07
    RYPTO
    -0.06
    _cred
    -0.06
    redient
    -0.06
    ÑĸÑģÑĤ
    -0.06
    loub
    -0.06
    POSITIVE LOGITS
    LF
    0.07
    alytics
    0.06
    988
    0.06
    035
    0.06
    arges
    0.06
    alysis
    0.06
     Carl
    0.05
    990
    0.05
    je
    0.05
     bo
    0.05
    Activations Density 0.006%

    No Known Activations