© 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. 95655
    Prev
    Next
    INDEX
    Explanations

    expressions related to diverse job roles and workplace experiences

    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
     Evening
    -0.06
    oid
    -0.06
    anium
    -0.06
     breeze
    -0.06
    aries
    -0.06
    unate
    -0.06
    .unbind
    -0.06
     bew
    -0.06
    dete
    -0.06
    rung
    -0.05
    POSITIVE LOGITS
     konkrét
    0.07
    -counter
    0.07
    enty
    0.07
    Sdk
    0.06
    adge
    0.06
    avin
    0.06
    ÏĦÏħ
    0.06
    =row
    0.06
    Responder
    0.06
    /avatar
    0.06
    Activations Density 0.074%

    No Known Activations