© 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. 40266
    Prev
    Next
    INDEX
    Explanations

    detailed financial transactions and stock holdings

    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
    .scalablytyped
    -0.08
    stein
    -0.08
     Hass
    -0.07
    ÑģÑĤе
    -0.07
    ailles
    -0.07
    ofilm
    -0.07
    ches
    -0.07
    stown
    -0.06
    onga
    -0.06
    ycin
    -0.06
    POSITIVE LOGITS
    ycz
    0.07
     indirect
    0.07
     stake
    0.07
     ownership
    0.06
     INDIRECT
    0.06
    rollers
    0.06
    isse
    0.06
    bol
    0.06
     иÑĤ
    0.06
     owning
    0.06
    Activations Density 0.003%

    No Known Activations