© 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. 118577
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance of elements related to education and personal development

    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
    uga
    -0.07
    .Formatter
    -0.07
    igan
    -0.07
    гÑĥ
    -0.07
    ually
    -0.06
     Markus
    -0.06
    arshal
    -0.06
    ONY
    -0.06
    KA
    -0.06
    ellas
    -0.06
    POSITIVE LOGITS
     thing
    0.08
     ingredient
    0.08
    bove
    0.08
    ssue
    0.07
    thing
    0.07
     Thing
    0.07
    eva
    0.07
     Ingredient
    0.07
    untu
    0.06
    ingredient
    0.06
    Activations Density 0.011%

    No Known Activations