© 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. 16848
    Prev
    Next
    INDEX
    Explanations

    timestamps and references within written content

    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
     Kot
    -0.07
    大人
    -0.07
    æŀIJ
    -0.07
     Grape
    -0.06
    .Σ
    -0.06
    Ỽ
    -0.06
     Mastery
    -0.06
    براÛĮ
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    lıģının
    -0.06
    POSITIVE LOGITS
    ecast
    0.07
    ìľ¼ëĭĪ
    0.06
    /logger
    0.06
    getOrElse
    0.06
    ollen
    0.06
    _clip
    0.06
    quer
    0.06
    [in
    0.06
    xffffffff
    0.06
    ouis
    0.06
    Activations Density 0.000%

    No Known Activations