© 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. 17-LLAMASCOPE-RES-131K
    6. 74892
    Prev
    Next
    INDEX
    Explanations

    phrases related to producing and distributing various forms of content or information

    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
     whe
    -0.06
    IPA
    -0.06
     дог
    -0.06
     Berk
    -0.06
    erp
    -0.06
    itez
    -0.06
    ToObject
    -0.05
    isis
    -0.05
    ledge
    -0.05
     rib
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    $core
    0.08
     ÑģкладÑĥ
    0.07
     stol
    0.07
    sburg
    0.07
    ìĦ¸
    0.07
    ãĥ¼ãĥijãĥ¼
    0.07
    ázev
    0.07
    itive
    0.07
    _warnings
    0.07
    Activations Density 0.012%

    No Known Activations