© 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. 125798
    Prev
    Next
    INDEX
    Explanations

    verbs indicating state or condition

    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
    *=*=
    -0.07
    morgan
    -0.07
    Suffix
    -0.07
    mojom
    -0.07
    898
    -0.07
    дап
    -0.07
    lÃŃd
    -0.07
    	Copyright
    -0.06
    tfoot
    -0.06
    ä¼Ŀ
    -0.06
    POSITIVE LOGITS
    inz
    0.07
     jud
    0.06
    ado
    0.06
     Juda
    0.06
    osp
    0.06
    eding
    0.06
    aviest
    0.06
    ãģĻãĤĮãģ°
    0.06
     preceded
    0.06
     Feder
    0.06
    Activations Density 0.107%

    No Known Activations