© 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. 15-LLAMASCOPE-RES-131K
    11. 61560
    Prev
    Next
    INDEX
    Explanations

    instances of uniqueness or first occurrences 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
     Bibli
    -0.06
    oman
    -0.06
     Loren
    -0.06
    FX
    -0.06
    inati
    -0.06
     everything
    -0.06
    kup
    -0.05
    288
    -0.05
    anta
    -0.05
     stuff
    -0.05
    POSITIVE LOGITS
    'gc
    0.09
    uforia
    0.08
    ï¼
    0.08
    imson
    0.07
     à¤IJस
    0.07
    #aa
    0.07
    readcr
    0.07
    .sax
    0.07
    InstanceId
    0.07
    .navigator
    0.07
    Activations Density 0.010%

    No Known Activations