Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106727
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contextual phrases that indicate beliefs or shared experiences

    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
    omit
    -0.06
    etler
    -0.06
     Jaune
    -0.05
    umn
    -0.05
    iou
    -0.05
     Dj
    -0.05
    jee
    -0.05
    :CGRect
    -0.05
     appet
    -0.05
     Bent
    -0.05
    POSITIVE LOGITS
    rog
    0.08
    andr
    0.07
    .scalablytyped
    0.07
    oblin
    0.07
    746
    0.07
     milan
    0.07
    ikel
    0.07
    éré
    0.07
    (strtolower
    0.07
    /goto
    0.07
    Activations Density 0.024%

    No Known Activations