Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106147
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    etc
    -0.06
    sat
    -0.06
     Arcade
    -0.06
     short
    -0.06
     Belt
    -0.06
    posium
    -0.06
     analysis
    -0.06
    yn
    -0.06
    tridge
    -0.06
    izu
    -0.05
    POSITIVE LOGITS
     nues
    0.09
     bald
    0.07
    regon
    0.07
    âĻª
    0.07
    .priv
    0.07
    .getElements
    0.07
    lds
    0.07
    #ab
    0.07
    ï¼»
    0.07
    _ment
    0.07
    Activations Density 0.013%

    No Known Activations