Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43989
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs indicating state or action

    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
    ampp
    -0.07
    ilde
    -0.07
    ÏĦÏĥι
    -0.06
    une
    -0.06
    _disp
    -0.06
    γη
    -0.06
    ä¿Ĺ
    -0.06
    borne
    -0.06
    uce
    -0.06
    arp
    -0.06
    POSITIVE LOGITS
     unaware
    0.09
     aware
    0.09
     expecting
    0.09
     written
    0.08
     designed
    0.08
     based
    0.08
     archit
    0.08
     using
    0.08
     opinion
    0.08
    aware
    0.07
    Activations Density 0.052%

    No Known Activations