© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3749
    Prev
    Next
    INDEX
    Explanations

    structural elements and definitions related to mathematical proofs

    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
    keley
    -0.07
    luk
    -0.07
     Jae
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    nee
    -0.06
    abcdefghijklmnop
    -0.06
    jal
    -0.06
     Òij
    -0.06
     derivation
    -0.06
    enderit
    -0.06
    POSITIVE LOGITS
     lemma
    0.17
     theorem
    0.17
     Cor
    0.15
     cor
    0.15
    theorem
    0.14
    lemma
    0.14
     Lem
    0.14
     Lemma
    0.14
     proposition
    0.14
    Lemma
    0.13
    Activations Density 0.832%

    No Known Activations