© 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. 96793
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or technical structures

    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
     Bits
    -0.07
    acf
    -0.06
    angelog
    -0.06
    никÑĥ
    -0.06
    teste
    -0.06
    ió
    -0.06
    imals
    -0.06
    غات
    -0.06
    ¶Į
    -0.06
    .djang
    -0.06
    POSITIVE LOGITS
     CIS
    0.08
    lint
    0.06
    ály
    0.06
    lim
    0.06
    ¯
    0.06
    onne
    0.06
    usch
    0.06
    alan
    0.06
    unt
    0.06
    213
    0.06
    Activations Density 0.392%

    No Known Activations