© 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. 87589
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" and variants thereof

    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
    eteria
    -0.07
    ufac
    -0.07
    tright
    -0.07
    uito
    -0.07
    еÑĤелÑĮ
    -0.07
    паÑĤ
    -0.07
    _lifetime
    -0.06
    ryn
    -0.06
    otes
    -0.06
    soon
    -0.06
    POSITIVE LOGITS
    /Edit
    0.07
    ocracy
    0.07
    jvu
    0.07
     Yourself
    0.07
     yourself
    0.06
    rlen
    0.06
    ارات
    0.06
    NameValuePair
    0.06
    ernen
    0.06
    tems
    0.06
    Activations Density 0.016%

    No Known Activations