© 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. 80299
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates and modifications in a system or data context

    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
    YRO
    -0.08
    uraa
    -0.08
    ãĥ³ãĥĸ
    -0.08
     youre
    -0.07
    berger
    -0.07
    Ñĥмов
    -0.07
    Alternate
    -0.07
    -initialized
    -0.06
    imbus
    -0.06
    pace
    -0.06
    POSITIVE LOGITS
     should
    0.07
    abra
    0.07
     automatically
    0.07
     Should
    0.07
    autom
    0.06
     vice
    0.06
    igm
    0.06
    orp
    0.06
    lej
    0.06
    ucken
    0.06
    Activations Density 0.004%

    No Known Activations