© 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. 15-LLAMASCOPE-RES-131K
    11. 98
    Prev
    Next
    INDEX
    Explanations

    historical references or significant introductory phrases

    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
    ucht
    -0.07
    rom
    -0.06
    luet
    -0.06
    ucs
    -0.06
     Vaugh
    -0.06
    è¯ij
    -0.06
    inen
    -0.06
    ategorized
    -0.06
    enburg
    -0.06
    arket
    -0.06
    POSITIVE LOGITS
     earliest
    0.07
     usage
    0.07
     deprecated
    0.07
    ÅĻeh
    0.07
     SND
    0.07
    samp
    0.07
     filmy
    0.07
    eyim
    0.07
    æĤł
    0.07
    188
    0.06
    Activations Density 0.003%

    No Known Activations