© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72901
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of gratitude

    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
    mite
    -0.07
    idon
    -0.07
    áºŃm
    -0.07
    наÑĢ
    -0.07
    озÑı
    -0.07
     Ekon
    -0.07
    :;↵
    -0.07
    hof
    -0.07
    AppState
    -0.07
    htar
    -0.06
    POSITIVE LOGITS
    /stdc
    0.06
    olu
    0.06
     dit
    0.06
    -valu
    0.06
    ovel
    0.06
    anni
    0.06
    dit
    0.06
    angstrom
    0.06
    @qq
    0.06
    aret
    0.06
    Activations Density 0.015%

    No Known Activations