© 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. 17-LLAMASCOPE-RES-131K
    11. 57167
    Prev
    Next
    INDEX
    Explanations

    references to future details or additional information

    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
    aklı
    -0.09
    .AF
    -0.07
    abox
    -0.07
    encies
    -0.07
    RIORITY
    -0.07
    åĨ
    -0.07
    ̧
    -0.07
    olini
    -0.07
    ourg
    -0.07
    Href
    -0.07
    POSITIVE LOGITS
     than
    0.08
    than
    0.07
     below
    0.07
     about
    0.06
     Burnett
    0.06
    rin
    0.06
     Than
    0.06
     elsewhere
    0.06
     later
    0.06
    ubo
    0.05
    Activations Density 0.003%

    No Known Activations