© 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. 9-LLAMASCOPE-RES-131K
    11. 98611
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements of a recipe or formula

    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
     +:+
    -0.07
    شت
    -0.07
    279
    -0.06
    >\<
    -0.06
    len
    -0.06
    amer
    -0.06
    illes
    -0.06
    à¹Ĥà¸ķ
    -0.06
    oplevel
    -0.06
     Sect
    -0.06
    POSITIVE LOGITS
    prung
    0.07
    ÑĨиÑĤ
    0.07
    اÙĨÙĩ
    0.07
     AsyncStorage
    0.07
    rowse
    0.07
    æĺŃ
    0.07
    emouth
    0.06
    ILD
    0.06
    .addHandler
    0.06
    ÐĦ
    0.06
    Activations Density 0.001%

    No Known Activations