© 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. 84103
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    ardin
    -0.07
    ÙĬÙĥÙĬ
    -0.07
    uards
    -0.06
    asha
    -0.06
    le
    -0.06
    ry
    -0.06
    itin
    -0.06
    ÛĮØ´ÙĨ
    -0.06
    avir
    -0.06
     اط
    -0.06
    POSITIVE LOGITS
     moment
    0.09
    ç®Ģåįķ
    0.09
     simple
    0.09
    maj
    0.07
     momento
    0.07
     SIMPLE
    0.07
    olian
    0.07
     earliest
    0.07
    simple
    0.07
     standpoint
    0.07
    Activations Density 0.014%

    No Known Activations