© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3766
    Prev
    Next
    INDEX
    Explanations

    references to various programs or initiatives

    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
    rale
    -0.07
    emachine
    -0.07
    çĶ
    -0.07
    .setViewport
    -0.07
    rias
    -0.07
    UPER
    -0.07
    .Middle
    -0.06
    alley
    -0.06
    __;
    -0.06
     activeClassName
    -0.06
    POSITIVE LOGITS
    matic
    0.08
     Carp
    0.07
    åijĺ
    0.07
    oth
    0.07
    atic
    0.06
    (Program
    0.06
    apolis
    0.06
    mond
    0.06
    åĵ¡
    0.06
    med
    0.06
    Activations Density 0.016%

    No Known Activations