© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29050
    Prev
    Next
    INDEX
    Explanations

    references to monetary costs and financial estimates

    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
     practically
    -0.06
     rem
    -0.06
     excuse
    -0.06
    erved
    -0.06
    RegExp
    -0.05
    884
    -0.05
     vic
    -0.05
     imm
    -0.05
     unp
    -0.05
     discontin
    -0.05
    POSITIVE LOGITS
     project
    0.11
     costs
    0.10
    project
    0.09
     cost
    0.09
    oproject
    0.09
    cost
    0.09
     пÑĢоекÑĤ
    0.09
     пÑĢоекÑĤÑĥ
    0.09
    _costs
    0.08
     projekt
    0.08
    Activations Density 0.026%

    No Known Activations