© 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. 69535
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly 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
     unlike
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
     sp
    -0.06
     afterwards
    -0.06
    ,
    -0.06
     whom
    -0.05
     ref
    -0.05
     intellig
    -0.05
     besides
    -0.05
    ovÃŃ
    -0.05
    POSITIVE LOGITS
     Similarly
    0.10
     similarly
    0.09
    Similarly
    0.09
     Likewise
    0.08
    dit
    0.08
     Meanwhile
    0.08
     Já
    0.07
    mpar
    0.07
    ifa
    0.07
     respecto
    0.07
    Activations Density 0.013%

    No Known Activations