© 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. 566
    Prev
    Next
    INDEX
    Explanations

    code block closure syntax in programming

    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
    antro
    -0.06
    anned
    -0.06
     right
    -0.06
    ml
    -0.06
    lesen
    -0.05
     fault
    -0.05
    ennon
    -0.05
     split
    -0.05
     definite
    -0.05
    #Region
    -0.05
    POSITIVE LOGITS
    iliar
    0.07
    ALAR
    0.07
    atÃŃm
    0.07
    andin
    0.06
    ëijĺ
    0.06
    aat
    0.06
    AGMA
    0.06
    á¹
    0.06
    ç£
    0.06
    ctor
    0.06
    Activations Density 0.022%

    No Known Activations