© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    technical terms and interactions related to multimedia management and programming

    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
     BITTE
    -0.08
    åŀ
    -0.08
    dum
    -0.07
    abcdefghijklmnop
    -0.07
     onAnimation
    -0.07
     zdrav
    -0.07
    :!
    -0.07
    á»ķ
    -0.07
    çĨ
    -0.07
    ัà¸Ĵ
    -0.07
    POSITIVE LOGITS
     Ear
    0.05
    Enlarge
    0.05
     NOT
    0.05
    raud
    0.05
    ouse
    0.05
    seealso
    0.05
     Certification
    0.05
    ei
    0.05
     Bowie
    0.05
    */
    0.05
    Activations Density 0.116%

    No Known Activations