© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 86204
    Prev
    Next
    INDEX
    Explanations

    instances of specific character sequences or formatting within code

    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
     Fucking
    -0.08
     Fuck
    -0.07
     assh
    -0.07
    fuck
    -0.07
     shit
    -0.07
     asshole
    -0.06
     fuck
    -0.06
     fucked
    -0.06
    zeÅĦ
    -0.06
     shitty
    -0.06
    POSITIVE LOGITS
    /goto
    0.07
    Expose
    0.06
     Lad
    0.06
    ربÙĩ
    0.06
     Daly
    0.06
    :]
    0.06
    ãĤĥ
    0.06
    æļ
    0.06
    .openg
    0.06
     precisely
    0.06
    Activations Density 0.000%

    No Known Activations