© 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. 84536
    Prev
    Next
    INDEX
    Explanations

    key terms related to shipping and returns policies

    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
    vem
    -0.09
    .dsl
    -0.08
    ãĥ¼ãĤ¸
    -0.08
    ingleton
    -0.07
    vé
    -0.07
    ivent
    -0.07
    ftype
    -0.07
    esion
    -0.07
     جÙĦس
    -0.07
    imoto
    -0.07
    POSITIVE LOGITS
    ath
    0.07
     returning
    0.07
     return
    0.06
     returns
    0.06
    ctest
    0.06
    bart
    0.06
     Bru
    0.06
     Returning
    0.06
     RETURNS
    0.06
     ins
    0.06
    Activations Density 0.005%

    No Known Activations