© 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. 17548
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions that connect ideas or phrases 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
    lut
    -0.07
    acic
    -0.06
    ios
    -0.06
    gan
    -0.06
    ll
    -0.06
     ########.
    -0.06
    igs
    -0.06
    icion
    -0.06
    jes
    -0.06
    ard
    -0.06
    POSITIVE LOGITS
     adr
    0.08
    .nt
    0.07
    ısından
    0.07
    (PC
    0.07
     siz
    0.07
    нимаеÑĤ
    0.06
    ãĤ¸ãĤ§
    0.06
    å¿ł
    0.06
    _NT
    0.06
    .pb
    0.06
    Activations Density 0.167%

    No Known Activations