© 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. 130695
    Prev
    Next
    INDEX
    Explanations

    financial implications and performance metrics of a film or production

    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
    анÑĮ
    -0.06
    alic
    -0.06
    ahl
    -0.06
    idl
    -0.05
    ãĥ©ãĥĥãĤ¯
    -0.05
     ev
    -0.05
     effectively
    -0.05
     occasionally
    -0.05
    AMB
    -0.05
    amb
    -0.05
    POSITIVE LOGITS
     unless
    0.10
    unless
    0.10
     likely
    0.10
    likely
    0.10
     Likely
    0.09
     possibly
    0.09
    resco
    0.09
     Äĩe
    0.09
     Unless
    0.08
    ãĥ³ãĤº
    0.08
    Activations Density 0.034%

    No Known Activations