© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95524
    Prev
    Next
    INDEX
    Explanations

    code elements related to the definition and use of modules in programming

    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
    arro
    -0.08
    ploy
    -0.06
    axon
    -0.06
    LOSE
    -0.06
     Gri
    -0.06
    ?f
    -0.06
    uffled
    -0.06
    udios
    -0.06
    ura
    -0.05
     lobby
    -0.05
    POSITIVE LOGITS
    нина
    0.07
    ekli
    0.07
    ÏĦιÏĥ
    0.07
    رÛĮاÙĨ
    0.06
    iglia
    0.06
     Opr
    0.06
    .snap
    0.06
    .rev
    0.06
    benh
    0.06
     hữu
    0.06
    Activations Density 0.000%

    No Known Activations