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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71037
    Prev
    Next
    INDEX
    Explanations

    references to government positions and affiliations

    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
    ahat
    -0.08
    PFN
    -0.06
    olta
    -0.06
    @js
    -0.06
    DCALL
    -0.06
    omik
    -0.06
    .selenium
    -0.06
    ¯u
    -0.06
    isl
    -0.06
    ìĹ´
    -0.06
    POSITIVE LOGITS
    asser
    0.08
    .sourceforge
    0.06
     Applied
    0.06
     applied
    0.06
    OptionPane
    0.06
    .googlecode
    0.06
    .analysis
    0.06
    abal
    0.06
    ITTER
    0.06
    ì²
    0.06
    Activations Density 0.014%

    No Known Activations