© 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. 76800
    Prev
    Next
    INDEX
    Explanations

    quotation marks and similar punctuation

    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
     jam
    -0.08
    jam
    -0.07
     Hodg
    -0.07
    üss
    -0.06
     имÑĥ
    -0.06
    à¸ļรร
    -0.06
    λÏİ
    -0.06
    azu
    -0.05
    TestClass
    -0.05
    eof
    -0.05
    POSITIVE LOGITS
    .TAG
    0.07
     collectively
    0.07
    oppers
    0.07
    imeType
    0.07
    stoi
    0.07
    ardin
    0.06
    reeze
    0.06
    otlin
    0.06
    acha
    0.06
    yg
    0.06
    Activations Density 0.002%

    No Known Activations