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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87523
    Prev
    Next
    INDEX
    Explanations

    variations of the word "full."

    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
    off
    -0.07
     crow
    -0.06
     Superior
    -0.06
     majority
    -0.06
    pen
    -0.06
     prob
    -0.06
     Animal
    -0.06
     loc
    -0.06
    ãĥ¬ãĤ¤
    -0.05
    icon
    -0.05
    POSITIVE LOGITS
     nuru
    0.08
    msgid
    0.08
    OKIE
    0.08
    ród
    0.08
    eydi
    0.07
    _lengths
    0.07
    enha
    0.07
    -lnd
    0.07
    ázev
    0.07
    ndl
    0.07
    Activations Density 0.003%

    No Known Activations