© 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. 4140
    Prev
    Next
    INDEX
    Explanations

    occurrences of names, titles, or distinguishing features related to locations and groups

    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
    olum
    -0.07
    uple
    -0.06
    gn
    -0.05
    .Mode
    -0.05
     mode
    -0.05
    intl
    -0.05
    wald
    -0.05
    aversal
    -0.05
     equivalents
    -0.05
    list
    -0.05
    POSITIVE LOGITS
     became
    0.10
     hence
    0.10
     eventually
    0.10
     Became
    0.09
     Eventually
    0.09
    Eventually
    0.09
     Hence
    0.08
    bec
    0.08
     later
    0.08
    ence
    0.07
    Activations Density 0.011%

    No Known Activations