© 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. 83343
    Prev
    Next
    INDEX
    Explanations

    structured data formats and specific code syntax elements

    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
    å±±å¸Ĥ
    -0.07
    ostel
    -0.07
    conomy
    -0.07
    azzi
    -0.07
    rzy
    -0.06
    IIIK
    -0.06
    ocre
    -0.06
    gaard
    -0.06
    WEB
    -0.06
    recht
    -0.06
    POSITIVE LOGITS
     Barbar
    0.06
    uster
    0.06
     Barber
    0.06
    obia
    0.06
    undi
    0.06
     DX
    0.06
    одав
    0.06
    ãģķãĤī
    0.06
    ennes
    0.06
    andid
    0.06
    Activations Density 0.044%

    No Known Activations