© 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. 61271
    Prev
    Next
    INDEX
    Explanations

    terms related to high-quality or elite products, concepts, or classification

    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
     Hayes
    -0.06
     Parkinson
    -0.06
    hof
    -0.06
    kees
    -0.06
    less
    -0.06
    anko
    -0.06
    zag
    -0.06
    buzz
    -0.06
    izard
    -0.06
    tu
    -0.06
    POSITIVE LOGITS
     SUPER
    0.10
     Super
    0.10
    ordinate
    0.10
     super
    0.10
    (super
    0.10
    Super
    0.09
     siêu
    0.09
    uper
    0.09
     è¶ħ
    0.08
    SUPER
    0.08
    Activations Density 0.039%

    No Known Activations