© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90728
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Lang" and its variations

    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
    ity
    -0.08
    stå
    -0.08
    ants
    -0.07
    quia
    -0.07
    aire
    -0.07
    bery
    -0.07
    ectomy
    -0.07
    ildo
    -0.06
    ãĥ£
    -0.06
    leaf
    -0.06
    POSITIVE LOGITS
    -speaking
    0.07
    åĭĻ
    0.07
    subst
    0.06
    olan
    0.06
    ISH
    0.06
    ycop
    0.06
    uien
    0.06
     exh
    0.06
     tslib
    0.06
    rie
    0.06
    Activations Density 0.008%

    No Known Activations