© 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. 1763
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing relationships or connections

    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
    blr
    -0.09
    еÑĢÑĪ
    -0.08
    enate
    -0.08
    ile
    -0.07
    ùng
    -0.07
    ÑĤÑİ
    -0.07
    chg
    -0.07
    pekt
    -0.07
     POSSIBILITY
    -0.07
    iyan
    -0.07
    POSITIVE LOGITS
    -sort
    0.08
    ocker
    0.07
     thing
    0.07
    -ÑĤаки
    0.07
    thing
    0.07
    /s
    0.07
    tml
    0.06
     semi
    0.06
    awks
    0.06
     à¹Ĩ
    0.06
    Activations Density 0.008%

    No Known Activations