© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127125
    Prev
    Next
    INDEX
    Explanations

    legal references or specific case identifiers

    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
     Eb
    -0.06
     forth
    -0.06
    hev
    -0.06
    oooooooo
    -0.06
    ebek
    -0.06
    ipated
    -0.06
    quisites
    -0.06
    ophy
    -0.06
    ìĦ¤
    -0.06
    gw
    -0.06
    POSITIVE LOGITS
    lander
    0.08
    ucher
    0.06
     ActionType
    0.06
    Ñĩик
    0.06
    umar
    0.06
     BaseService
    0.06
     ÎijÎĵ
    0.06
    ijken
    0.06
    lobal
    0.06
    оÑĢоÑĤ
    0.06
    Activations Density 0.001%

    No Known Activations