Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128798
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly those used to signify the end of a statement or thought

    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
    if
    -0.06
    je
    -0.06
    ей
    -0.06
    esch
    -0.06
    xima
    -0.06
    afs
    -0.06
    optera
    -0.06
    dan
    -0.06
    ne
    -0.06
    _
    -0.06
    POSITIVE LOGITS
    jpg
    0.09
    tte
    0.08
     addCriterion
    0.07
    ickerView
    0.07
    ,");↵
    0.07
    .zh
    0.06
    rani
    0.06
    png
    0.06
    TestingModule
    0.06
    payments
    0.06
    Activations Density 0.049%

    No Known Activations