© 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. 55894
    Prev
    Next
    INDEX
    Explanations

    verbs associated with professional or collaborative efforts

    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
    nip
    -0.07
    oria
    -0.07
    unday
    -0.07
     Rad
    -0.07
    uir
    -0.06
    omm
    -0.06
    ELY
    -0.06
    ù
    -0.06
    rek
    -0.06
     Cres
    -0.06
    POSITIVE LOGITS
     harder
    0.08
     towards
    0.07
     alongside
    0.07
    bench
    0.07
     together
    0.07
     toward
    0.06
    edd
    0.06
    åĿĬ
    0.06
    ite
    0.06
     withd
    0.06
    Activations Density 0.045%

    No Known Activations