© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    references to concrete in various contexts

    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
    istrovstvÃŃ
    -0.09
    ëĿ½
    -0.08
    lying
    -0.07
    tright
    -0.07
    è¾°
    -0.07
    run
    -0.07
    marks
    -0.07
     Dere
    -0.07
    .Charting
    -0.07
    upe
    -0.07
    POSITIVE LOGITS
    itious
    0.08
    hower
    0.07
    angelo
    0.07
     Jungle
    0.06
     slab
    0.06
    cki
    0.06
    clid
    0.06
    icious
    0.06
     jungle
    0.06
    HostName
    0.06
    Activations Density 0.002%

    No Known Activations