© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90705
    Prev
    Next
    INDEX
    Explanations

    words that indicate clarity or understanding in a context

    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
     sque
    -0.06
    /logger
    -0.06
     Danger
    -0.06
    u
    -0.05
     covered
    -0.05
    nat
    -0.05
     Grass
    -0.05
     She
    -0.05
     Mash
    -0.05
     &
    -0.05
    POSITIVE LOGITS
    	TokenName
    0.08
    turnstile
    0.08
    furt
    0.07
    uly
    0.07
    ildo
    0.07
     поÑĢÑıд
    0.07
    ána
    0.07
    .qq
    0.07
     Baz
    0.07
    .reader
    0.07
    Activations Density 0.000%

    No Known Activations