© 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. 90427
    Prev
    Next
    INDEX
    Explanations

    references to months and dates

    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
    iÄĩ
    -0.07
    jl
    -0.07
    AZY
    -0.07
     Fus
    -0.06
    itle
    -0.06
    vester
    -0.06
    orm
    -0.06
    instant
    -0.06
    çŀ¬
    -0.06
    mux
    -0.06
    POSITIVE LOGITS
    aeper
    0.08
     respectively
    0.07
    ular
    0.07
    ownt
    0.07
     alike
    0.07
    istributor
    0.07
    izzo
    0.07
    äll
    0.06
    °С
    0.06
    tvrt
    0.06
    Activations Density 0.006%

    No Known Activations