© 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. 15-LLAMASCOPE-RES-131K
    6. 62423
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gather" and its variations, indicating a focus on gatherings or community 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
    ovan
    -0.07
     latter
    -0.07
    amespace
    -0.07
    äge
    -0.07
    portun
    -0.07
    utow
    -0.07
    iminal
    -0.07
    kers
    -0.07
    yu
    -0.07
    imal
    -0.06
    POSITIVE LOGITS
    ings
    0.10
    (Collectors
    0.08
    ments
    0.08
    inge
    0.07
    INGS
    0.07
     slack
    0.07
    orum
    0.07
     ÑĥÑĢож
    0.07
    -sama
    0.07
    ocity
    0.06
    Activations Density 0.010%

    No Known Activations