© 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. 86069
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" followed by times of change or significant events

    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
    aki
    -0.07
    :UIAlert
    -0.06
    antee
    -0.06
    tron
    -0.06
    ¢åįķ
    -0.06
    foy
    -0.06
    jure
    -0.05
    atr
    -0.05
    ead
    -0.05
    quette
    -0.05
    POSITIVE LOGITS
    ÅĻeba
    0.08
    ovÃŃ
    0.08
    sı
    0.07
    .$.
    0.07
    è¡ĵ
    0.07
    nesc
    0.06
    alles
    0.06
    _Space
    0.06
    deme
    0.06
    änner
    0.06
    Activations Density 0.030%

    No Known Activations