© 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 EvalsExportsinterp-engineNEWAPI 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. 18209
    Prev
    Next
    INDEX
    Explanations

    references to personal or organizational information and data collection practices

    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
    iao
    -0.06
    108
    -0.06
    ÑĢем
    -0.06
    100
    -0.05
    ł
    -0.05
     Ha
    -0.05
    rix
    -0.05
    emem
    -0.05
    Ger
    -0.05
    iter
    -0.05
    POSITIVE LOGITS
    okable
    0.07
    .codes
    0.07
    .scalablytyped
    0.07
    áºŃu
    0.07
    zych
    0.07
     Via
    0.07
    _via
    0.07
    GTK
    0.07
    pNet
    0.07
    Æ°u
    0.07
    Activations Density 0.002%

    No Known Activations