© 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. 84437
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or geopolitical entities

    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
    wald
    -0.08
    prung
    -0.07
    amma
    -0.07
     Gaz
    -0.07
    pir
    -0.07
    .scalablytyped
    -0.07
    ALCHEMY
    -0.07
    pf
    -0.07
     isChecked
    -0.07
    ycop
    -0.06
    POSITIVE LOGITS
    asley
    0.06
    461
    0.06
    riel
    0.06
    رÙĩ
    0.06
    okable
    0.06
    yre
    0.06
    OCUS
    0.06
    861
    0.06
    halt
    0.06
    rient
    0.06
    Activations Density 0.004%

    No Known Activations