© 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. 130303
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, which may indicate the end of sentences or points being made in the text

    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
    ationally
    -0.08
    aktu
    -0.07
    askan
    -0.07
    rong
    -0.07
    alles
    -0.07
    ìĬ¤ì½Ķ
    -0.07
     *)((
    -0.07
    ytt
    -0.07
    bery
    -0.07
    ongyang
    -0.06
    POSITIVE LOGITS
    938
    0.06
    Bron
    0.06
    ahy
    0.06
    fix
    0.05
    illow
    0.05
    apon
    0.05
    lov
    0.05
     Miche
    0.05
    uron
    0.05
    icode
    0.05
    Activations Density 0.006%

    No Known Activations