© 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. 89698
    Prev
    Next
    INDEX
    Explanations

    the presence of the words "on" and "in" within various contexts

    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
    ius
    -0.06
    mpl
    -0.06
    знаÑĩа
    -0.06
    lamp
    -0.06
    junction
    -0.06
    erus
    -0.06
    ÅĤaw
    -0.06
     conex
    -0.06
    ning
    -0.06
    ued
    -0.06
    POSITIVE LOGITS
    Ấ
    0.07
    ạ
    0.07
    -to
    0.07
    alette
    0.07
    arges
    0.07
    اÛĮÙĩ
    0.07
     prime
    0.06
    ster
    0.06
    sth
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    Activations Density 0.017%

    No Known Activations