© 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. 106080
    Prev
    Next
    INDEX
    Explanations

    elements related to web content and navigation URLs

    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
    keh
    -0.08
    гÑĢад
    -0.07
    afs
    -0.07
    llib
    -0.07
     treff
    -0.07
    _syntax
    -0.07
    ç³»
    -0.07
    /cgi
    -0.07
    reon
    -0.07
    reo
    -0.07
    POSITIVE LOGITS
    .html
    0.08
    .php
    0.07
     form
    0.06
    ί
    0.06
    .shtml
    0.06
    ?id
    0.06
    .htm
    0.06
    =true
    0.05
     princip
    0.05
    odel
    0.05
    Activations Density 0.016%

    No Known Activations