© 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. 27226
    Prev
    Next
    INDEX
    Explanations

    questions about the degree or extent of something

    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
    isa
    -0.06
     will
    -0.06
     whose
    -0.06
    aval
    -0.06
     /
    -0.06
     :
    -0.06
     w
    -0.06
    icens
    -0.05
     On
    -0.05
     with
    -0.05
    POSITIVE LOGITS
    HEME
    0.09
    eck
    0.08
    ëĿ½
    0.08
    egree
    0.08
    ุà¹ī
    0.08
    ToProps
    0.08
    ££
    0.08
    rych
    0.08
    ateur
    0.08
    yl
    0.07
    Activations Density 0.017%

    No Known Activations