© 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. 3905
    Prev
    Next
    INDEX
    Explanations

    statements expressing personal beliefs or opinions

    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
    ValueChanged
    -0.08
    âng
    -0.07
    é¬
    -0.07
    cia
    -0.07
    ierre
    -0.07
    itten
    -0.06
    OptionsMenu
    -0.06
    بات
    -0.06
    lero
    -0.06
    angel
    -0.06
    POSITIVE LOGITS
     Tavern
    0.06
     Moff
    0.06
     opinion
    0.06
     view
    0.05
    .nih
    0.05
    adin
    0.05
     Rae
    0.05
    åį°
    0.05
    esk
    0.05
    red
    0.05
    Activations Density 0.019%

    No Known Activations