© 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. 15-LLAMASCOPE-RES-131K
    11. 103815
    Prev
    Next
    INDEX
    Explanations

    instances of the word "copyright" and related terms

    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
    ilon
    -0.06
     Powell
    -0.06
    unks
    -0.06
    uk
    -0.06
     Crowley
    -0.06
    acock
    -0.06
    rlen
    -0.06
    _mB
    -0.06
    cks
    -0.06
     Injector
    -0.06
    POSITIVE LOGITS
     NUIT
    0.07
    ãĤ·ãĥ§
    0.07
    ym
    0.07
    å¿Ĺ
    0.07
    è¼Ķ
    0.07
    nest
    0.07
    oÄŁlu
    0.07
     HOLDERS
    0.07
    ULD
    0.07
    SOR
    0.06
    Activations Density 0.000%

    No Known Activations