© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128234
    Prev
    Next
    INDEX
    Explanations

    aspects related to historical or geographical descriptions

    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
    eree
    -0.07
    á»Ĩ
    -0.07
     Foo
    -0.07
     mountains
    -0.07
     rival
    -0.06
    ibs
    -0.06
     bead
    -0.06
     oceans
    -0.06
     Mellon
    -0.06
    @show
    -0.06
    POSITIVE LOGITS
    ÑĢиз
    0.07
     buffers
    0.06
     管
    0.06
    nea
    0.06
    luž
    0.06
    ÎIJ
    0.06
    ulg
    0.06
    artin
    0.06
     Invent
    0.06
    å¼¥
    0.06
    Activations Density 0.003%

    No Known Activations