© 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. 9-LLAMASCOPE-RES-131K
    11. 98762
    Prev
    Next
    INDEX
    Explanations

    instances of the word "particular" to identify specificity in context

    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
    andal
    -0.07
     wonder
    -0.07
    wap
    -0.06
    nze
    -0.06
    ikh
    -0.06
    yr
    -0.06
     as
    -0.06
     Wonder
    -0.06
    iet
    -0.06
     thus
    -0.06
    POSITIVE LOGITS
    esty
    0.08
    веÑī
    0.08
    .datatables
    0.07
    liness
    0.07
    .bpm
    0.07
    ificates
    0.07
     nokt
    0.07
    lue
    0.07
    otts
    0.07
    UME
    0.07
    Activations Density 0.005%

    No Known Activations