© 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. 62055
    Prev
    Next
    INDEX
    Explanations

    descriptions of perspectives and detailed character analyses

    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
    itten
    -0.07
    abbr
    -0.07
    ipe
    -0.06
    rna
    -0.06
    olis
    -0.06
    éru
    -0.06
    -chan
    -0.06
     háºŃu
    -0.06
    zan
    -0.06
    orsi
    -0.06
    POSITIVE LOGITS
     indent
    0.07
    PCS
    0.06
     bild
    0.06
     enclosed
    0.06
     passage
    0.06
    acl
    0.06
    bserv
    0.06
    aec
    0.06
     è±
    0.06
     Passage
    0.06
    Activations Density 0.054%

    No Known Activations