© 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. 42005
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically dashes

    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
    aseline
    -0.06
     hoa
    -0.06
    .enumer
    -0.06
     Nicholson
    -0.06
    rom
    -0.06
    ttp
    -0.06
     convent
    -0.06
    ÄĽ
    -0.05
    iface
    -0.05
    acl
    -0.05
    POSITIVE LOGITS
    556
    0.06
    hta
    0.06
    ean
    0.06
    άνι
    0.06
    arium
    0.06
     reli
    0.06
     irr
    0.06
    umer
    0.06
    294
    0.06
    олоÑģ
    0.06
    Activations Density 0.000%

    No Known Activations