© 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. 3681
    Prev
    Next
    INDEX
    Explanations

    phrases indicating challenges or difficulties faced by specific 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
    chez
    -0.09
    åħħ
    -0.09
    Äįku
    -0.08
    arend
    -0.07
    .dds
    -0.07
    -svg
    -0.07
    ÅĻez
    -0.07
    _globals
    -0.07
    ableViewController
    -0.07
    IOUS
    -0.07
    POSITIVE LOGITS
     any
    0.08
     even
    0.08
     many
    0.08
     us
    0.08
     unless
    0.07
     anyone
    0.07
     tab
    0.06
     sometimes
    0.06
     to
    0.06
    137
    0.06
    Activations Density 0.016%

    No Known Activations