© 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. 15-LLAMASCOPE-RES-131K
    11. 86885
    Prev
    Next
    INDEX
    Explanations

    sentences that include significant punctuation, especially periods

    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
    imon
    -0.07
    .rgb
    -0.06
    avis
    -0.06
    ãĥ¼ãĥį
    -0.06
    ASN
    -0.06
    pv
    -0.06
     dressing
    -0.06
    inand
    -0.06
    å½¹
    -0.06
    ãģŁãĤĬ
    -0.06
    POSITIVE LOGITS
     but
    0.09
     nhÆ°ng
    0.07
    ¤í
    0.06
    qid
    0.06
    eyse
    0.06
    ìĿ¸ëį°
    0.06
    Uvs
    0.06
    ä½Ĩ
    0.06
     however
    0.06
    ecided
    0.06
    Activations Density 0.025%

    No Known Activations