© 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. 86292
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics

    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
    Ngh
    -0.09
    ë¦Ħ
    -0.08
    Unsigned
    -0.08
    å³°
    -0.07
    ãģĵãĤĵ
    -0.07
    861
    -0.07
     полÑı
    -0.07
    "+"
    -0.07
     BÄĽ
    -0.07
    embros
    -0.07
    POSITIVE LOGITS
    UMB
    0.07
    ipp
    0.07
     MainAxisAlignment
    0.06
    adi
    0.05
    alore
    0.05
    eg
    0.05
    ¤
    0.05
     Faces
    0.05
    oad
    0.05
     Westbrook
    0.05
    Activations Density 0.098%

    No Known Activations