© 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. 54744
    Prev
    Next
    INDEX
    Explanations

    interactions involving the exchange of information and inquiries related to assistance or guidance

    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
    ardy
    -0.07
    ób
    -0.07
    365
    -0.07
    ailable
    -0.06
    ogo
    -0.06
    alta
    -0.06
    raith
    -0.06
    OWER
    -0.06
    ãĥIJãĤ¤
    -0.06
    ÑģÑĤÑİ
    -0.06
    POSITIVE LOGITS
     desired
    0.28
    desired
    0.23
     wanted
    0.21
     Desired
    0.20
    wanted
    0.17
     needed
    0.17
     Wanted
    0.15
     sought
    0.15
     required
    0.15
     desirable
    0.13
    Activations Density 0.165%

    No Known Activations