© 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. 22-LLAMASCOPE-RES-131K
    11. 4251
    Prev
    Next
    INDEX
    Explanations

    patterns and structures commonly found in programming or grammatical notation

    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
    uling
    -0.09
    paged
    -0.07
    ạ
    -0.07
     trif
    -0.07
    ernaut
    -0.06
    aram
    -0.06
    zv
    -0.06
    ãĥ¼ãĥŃ
    -0.06
    acio
    -0.06
    enta
    -0.06
    POSITIVE LOGITS
     pron
    0.14
     ad
    0.13
     adv
    0.11
     adj
    0.11
     Verb
    0.10
     Pron
    0.10
    Verb
    0.10
     Ad
    0.10
     Adj
    0.10
     conjunction
    0.09
    Activations Density 0.036%

    No Known Activations