© 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 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. 59138
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation characters used in code

    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
    arten
    -0.07
    ées
    -0.07
    r
    -0.06
    rane
    -0.06
     cred
    -0.06
    add
    -0.06
    arlo
    -0.06
    apur
    -0.06
     increments
    -0.06
    oh
    -0.06
    POSITIVE LOGITS
    ازد
    0.08
    /rss
    0.07
    ÑģÑĮого
    0.07
     имÑĥ
    0.07
    ija
    0.07
    åIJ¦
    0.07
    帯
    0.07
    иÑĢÑĥ
    0.06
    اط
    0.06
     Ore
    0.06
    Activations Density 0.000%

    No Known Activations