© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87051
    Prev
    Next
    INDEX
    Explanations

    numbers and parentheses in the text

    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
    uster
    -0.07
    acco
    -0.06
     Alejandro
    -0.06
    olet
    -0.06
    ails
    -0.06
    (s
    -0.06
    APT
    -0.06
     Raz
    -0.06
    abella
    -0.06
    eec
    -0.06
    POSITIVE LOGITS
     whereas
    0.08
    èĢĮ
    0.07
     Whereas
    0.07
    reff
    0.07
     equivalent
    0.06
    plus
    0.06
    ãĥĨãĥ«
    0.06
     compared
    0.06
    reed
    0.06
     Clarke
    0.06
    Activations Density 0.032%

    No Known Activations