© 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. 9-LLAMASCOPE-RES-131K
    11. 95594
    Prev
    Next
    INDEX
    Explanations

    financial data related to fundraising and campaign contributions

    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
     passed
    -0.06
     Bond
    -0.06
     fi
    -0.06
     incidental
    -0.06
     bond
    -0.06
     passing
    -0.06
     full
    -0.05
     fl
    -0.05
     i
    -0.05
    fi
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    маз
    0.08
    oord
    0.08
    ³
    0.07
    andest
    0.07
    prung
    0.07
    dden
    0.07
     Morm
    0.07
    ÑĢоÑĤив
    0.07
    езда
    0.07
    Activations Density 0.007%

    No Known Activations