© 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 EvalsExportsAPI 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. 84189
    Prev
    Next
    INDEX
    Explanations

    words related to support and improvement in various community and organizational contexts

    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
    //{{
    -0.08
     dara
    -0.08
    itler
    -0.07
    ookies
    -0.07
     Deniz
    -0.07
    виÑħ
    -0.07
    krom
    -0.07
     поба
    -0.07
    ãĤ¤ãĤº
    -0.07
    ngx
    -0.07
    POSITIVE LOGITS
    860
    0.06
     Bradley
    0.06
     Kin
    0.06
     FindObjectOfType
    0.06
    uml
    0.06
    usp
    0.06
     jlong
    0.06
    820
    0.06
     Sheridan
    0.05
    º
    0.05
    Activations Density 0.047%

    No Known Activations