© 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. 105769
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "your" and related forms

    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
    aida
    -0.07
    kus
    -0.07
    enÃŃ
    -0.07
    cid
    -0.07
    //{{
    -0.07
    éģ
    -0.07
    ãĥ³ãĤ¹
    -0.06
    laz
    -0.06
    δή
    -0.06
    _MUTEX
    -0.06
    POSITIVE LOGITS
     question
    0.08
     example
    0.07
    appro
    0.07
     approach
    0.07
     posted
    0.07
     Question
    0.06
    uien
    0.06
    0.06
    103
    0.06
     Example
    0.06
    Activations Density 0.006%

    No Known Activations