© 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. 1858
    Prev
    Next
    INDEX
    Explanations

    terms associated with irreversibility or irreparable damage

    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
    ETHOD
    -0.08
    orelease
    -0.08
    ãĥ£
    -0.07
    solete
    -0.07
    geries
    -0.07
    ronic
    -0.07
    Queryable
    -0.07
    paged
    -0.07
    INTERFACE
    -0.06
    .scalablytyped
    -0.06
    POSITIVE LOGITS
    ously
    0.08
    atively
    0.07
    eto
    0.07
    ments
    0.07
    ment
    0.07
    illy
    0.07
    axed
    0.07
    igon
    0.06
     patches
    0.06
    IGH
    0.06
    Activations Density 0.005%

    No Known Activations