© 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. 9-LLAMASCOPE-RES-131K
    11. 97156
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially periods and commas

    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
    otas
    -0.08
    avl
    -0.07
    RL
    -0.07
    ot
    -0.07
    lice
    -0.06
    ayment
    -0.06
    oon
    -0.06
    kaar
    -0.06
    idon
    -0.06
    ventional
    -0.06
    POSITIVE LOGITS
    orget
    0.06
    lew
    0.06
    ibase
    0.06
    aturas
    0.06
    -collapse
    0.06
    (fabs
    0.06
    utsch
    0.06
    rieben
    0.06
    -âĢIJ
    0.06
     ull
    0.06
    Activations Density 0.030%

    No Known Activations