© 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. 89499
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or exceptions in the narrative

    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
    agan
    -0.07
    arel
    -0.07
    attles
    -0.06
     Bris
    -0.06
    azor
    -0.06
     пÑĢиÑĩ
    -0.06
    ueil
    -0.06
    ÙIJÙĩ
    -0.06
    rear
    -0.06
    aggi
    -0.06
    POSITIVE LOGITS
     soon
    0.08
    utr
    0.07
    YPRE
    0.06
    OrNil
    0.06
    gnore
    0.06
     fires
    0.06
     Mes
    0.06
     gint
    0.05
    tractive
    0.05
    ozem
    0.05
    Activations Density 0.026%

    No Known Activations