© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26991
    Prev
    Next
    INDEX
    Explanations

    mentions of royalty and their titles

    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
    ovatel
    -0.08
    ubber
    -0.07
    oard
    -0.07
    imens
    -0.07
    OMIC
    -0.07
    odiac
    -0.07
    ODEV
    -0.07
    AMPL
    -0.07
    _macros
    -0.07
    aÄį
    -0.07
    POSITIVE LOGITS
     Grave
    0.06
    672
    0.06
    SCR
    0.06
     teng
    0.06
     Farrell
    0.06
    RAP
    0.06
     Jer
    0.05
    SZ
    0.05
    Compat
    0.05
    DC
    0.05
    Activations Density 0.004%

    No Known Activations