© 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. 107585
    Prev
    Next
    INDEX
    Explanations

    personal expressions and affirmations in speech

    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
    urr
    -0.09
    ouro
    -0.08
    Å¡lo
    -0.07
     LATIN
    -0.07
    iesz
    -0.07
    inosaur
    -0.07
    udeau
    -0.07
    shaw
    -0.07
    EXTERN
    -0.07
    irling
    -0.07
    POSITIVE LOGITS
     slides
    0.08
     Slide
    0.07
    çĩ
    0.07
     slide
    0.06
     Chair
    0.06
     thao
    0.06
    Remarks
    0.06
     digit
    0.06
    éĿ
    0.06
    doi
    0.06
    Activations Density 0.015%

    No Known Activations