© 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. 117035
    Prev
    Next
    INDEX
    Explanations

    instances of personal revelations or significant life changes

    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
    ÑĢоÑĪ
    -0.07
    ignal
    -0.07
    .promise
    -0.06
    ache
    -0.06
    ейÑĩаÑģ
    -0.06
    isode
    -0.06
    æĬĺ
    -0.06
    .Expressions
    -0.06
     conoc
    -0.06
    rav
    -0.06
    POSITIVE LOGITS
    561
    0.06
     Clarke
    0.06
    -Compatible
    0.06
    lix
    0.06
     Suspension
    0.06
     rece
    0.06
    ema
    0.06
    ammable
    0.06
     suspension
    0.06
    CEE
    0.06
    Activations Density 0.016%

    No Known Activations