© 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 EvalsExportsAPI 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. 131014
    Prev
    Next
    INDEX
    Explanations

    HTML or other markup language attributes and links

    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
    ory
    -0.06
     Gel
    -0.06
    ÑĢа
    -0.05
     æ¨
    -0.05
     Vers
    -0.05
     Higgins
    -0.05
     seja
    -0.05
     Sala
    -0.05
    esses
    -0.05
    iyi
    -0.05
    POSITIVE LOGITS
     Uncategorized
    0.07
    /../
    0.07
    rient
    0.07
    eyed
    0.07
    DonaldTrump
    0.07
    undos
    0.07
    ithe
    0.07
    irse
    0.07
    addtogroup
    0.07
     CHARSET
    0.07
    Activations Density 0.004%

    No Known Activations