© 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. 55956
    Prev
    Next
    INDEX
    Explanations

    references to notable achievements and recognitions in educational contexts

    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
     kultur
    -0.07
    shade
    -0.07
    mas
    -0.07
    Codes
    -0.06
     codes
    -0.06
     shade
    -0.06
    pillar
    -0.06
    codes
    -0.06
    ada
    -0.06
     nav
    -0.06
    POSITIVE LOGITS
     Directory
    0.09
    uario
    0.08
    Directory
    0.08
    directory
    0.08
    dge
    0.07
     directories
    0.07
     directory
    0.07
    .Directory
    0.07
    Enc
    0.07
    /profile
    0.07
    Activations Density 0.002%

    No Known Activations