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. 44020
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of founding and its associated historical implications

    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
    .elementAt
    -0.07
    endon
    -0.07
    'field
    -0.07
    Ïģίζ
    -0.07
    igli
    -0.07
    -send
    -0.07
    engkap
    -0.07
    ufe
    -0.07
    anzeigen
    -0.07
    cen
    -0.07
    POSITIVE LOGITS
     Fathers
    0.15
     fathers
    0.13
     Father
    0.12
     generation
    0.12
     documents
    0.11
     Documents
    0.10
     Fram
    0.10
     Found
    0.10
     Generation
    0.10
    athers
    0.09
    Activations Density 0.006%

    No Known Activations