© 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. 88571
    Prev
    Next
    INDEX
    Explanations

    references to dates and timelines

    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
    çijŀ
    -0.08
    kening
    -0.08
    μον
    -0.07
    کارÛĮ
    -0.07
    ÏĮÏĦε
    -0.07
     हव
    -0.07
    avax
    -0.07
    à¹Ģà¸Ĺศ
    -0.07
    å±±å¸Ĥ
    -0.07
    éħ
    -0.06
    POSITIVE LOGITS
    indre
    0.08
     end
    0.07
     after
    0.07
    rosso
    0.06
     basic
    0.06
     except
    0.06
     due
    0.06
    .end
    0.06
    Connection
    0.06
     sou
    0.06
    Activations Density 0.016%

    No Known Activations