© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71318
    Prev
    Next
    INDEX
    Explanations

    phrases that denote experience or involvement in a specific field or profession

    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
    ignKey
    -0.08
     esac
    -0.07
    \Collections
    -0.07
    aday
    -0.07
    esModule
    -0.07
    ease
    -0.06
    人çī©
    -0.06
     Besch
    -0.06
     PROCUREMENT
    -0.06
    arsity
    -0.06
    POSITIVE LOGITS
     interests
    0.08
     responsibility
    0.08
    olds
    0.08
     deep
    0.07
     whom
    0.07
     demonstrated
    0.07
     focus
    0.06
     responsibilities
    0.06
     a
    0.06
     growing
    0.06
    Activations Density 0.011%

    No Known Activations