© 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. 106376
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" and its forms in various 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
    á»IJ
    -0.08
    ména
    -0.08
    alim
    -0.07
    caff
    -0.07
    etin
    -0.07
    eydi
    -0.07
    .YesNo
    -0.07
     Král
    -0.07
    andin
    -0.07
     mát
    -0.07
    POSITIVE LOGITS
     turned
    0.07
     refused
    0.06
     tab
    0.06
     kit
    0.06
    nr
    0.06
     poste
    0.06
     po
    0.06
     ignored
    0.06
    ire
    0.05
    zee
    0.05
    Activations Density 0.022%

    No Known Activations