© 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. 93623
    Prev
    Next
    INDEX
    Explanations

    functional programming constructs or methods used in code

    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
    inis
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    داÙħ
    -0.07
    象
    -0.07
     Massive
    -0.06
    uling
    -0.06
    ofil
    -0.06
     crow
    -0.06
     whit
    -0.06
    ampp
    -0.06
    POSITIVE LOGITS
     lambda
    0.12
    (lambda
    0.11
    =lambda
    0.11
    :^(
    0.10
    lambda
    0.10
     function
    0.10
    λ
    0.09
    ,function
    0.07
    (function
    0.07
    CompleteListener
    0.07
    Activations Density 0.045%

    No Known Activations