© 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. 70374
    Prev
    Next
    INDEX
    Explanations

    abrupt shifts in tone or emphasis within the text

    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
    YLON
    -0.07
    utom
    -0.06
    ĵį
    -0.06
    raman
    -0.06
    itten
    -0.06
     Priv
    -0.06
    amped
    -0.06
    TargetException
    -0.06
    portunity
    -0.06
     CHO
    -0.06
    POSITIVE LOGITS
     ones
    0.20
    ones
    0.15
     Ones
    0.14
     those
    0.11
     such
    0.10
     whose
    0.09
    such
    0.09
    those
    0.09
     ceux
    0.09
     tÄĽch
    0.08
    Activations Density 0.061%

    No Known Activations