© 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. 59514
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wherever" and its variations indicating location or presence

    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
    alace
    -0.08
     RESERVED
    -0.07
    .scalablytyped
    -0.06
    amed
    -0.06
     sobie
    -0.06
    ilters
    -0.06
    olic
    -0.06
    gh
    -0.06
    омен
    -0.06
    spin
    -0.06
    POSITIVE LOGITS
    _possible
    0.08
    mis
    0.08
    ensi
    0.07
    NAL
    0.07
    lant
    0.07
    located
    0.07
    475
    0.07
    nda
    0.07
    oda
    0.06
     possible
    0.06
    Activations Density 0.004%

    No Known Activations