© 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. 9-LLAMASCOPE-RES-131K
    6. 95061
    Prev
    Next
    INDEX
    Explanations

    references to identity and personal anecdotes

    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
    rega
    -0.08
    odzi
    -0.07
    ITLE
    -0.07
    ζα
    -0.07
    iona
    -0.07
    estring
    -0.07
     tez
    -0.06
    icies
    -0.06
    statuses
    -0.06
    nea
    -0.06
    POSITIVE LOGITS
    vik
    0.06
    nee
    0.06
    323
    0.06
    gere
    0.05
     animate
    0.05
    von
    0.05
    ElementsBy
    0.05
     Downs
    0.05
    OMIC
    0.05
     Tin
    0.05
    Activations Density 0.001%

    No Known Activations