© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103836
    Prev
    Next
    INDEX
    Explanations

    programming code related to error handling and validation

    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
    oon
    -0.07
     Fra
    -0.06
    ambre
    -0.06
    oons
    -0.06
    -feedback
    -0.06
    afka
    -0.06
    omite
    -0.06
    ild
    -0.06
     Bra
    -0.06
    bon
    -0.06
    POSITIVE LOGITS
    ContentLoaded
    0.08
    æºĸ
    0.07
    bote
    0.07
     TValue
    0.07
    contents
    0.07
    åĨħ容
    0.07
    actices
    0.07
    setContent
    0.06
     payload
    0.06
    istencia
    0.06
    Activations Density 0.047%

    No Known Activations