© 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. 3196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a subset or selection of items or examples

    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
    fluence
    -0.07
     itself
    -0.06
    اÛĮÙĩ
    -0.06
    å¼ķãģį
    -0.06
    нд
    -0.06
    ýv
    -0.06
    adero
    -0.06
    yen
    -0.06
     alot
    -0.06
    ramework
    -0.06
    POSITIVE LOGITS
     ways
    0.09
     example
    0.08
     reasons
    0.08
     examples
    0.07
     tips
    0.07
     пÑĢимеÑĢ
    0.07
     Nack
    0.07
     recent
    0.07
    typ
    0.07
     найб
    0.07
    Activations Density 0.010%

    No Known Activations