© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15682
    Prev
    Next
    INDEX
    Explanations

    the word "thing" and its variations

    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
     ÑĤакими
    -0.06
    /tos
    -0.06
    .twitch
    -0.06
    EXTERN
    -0.06
    иÑģÑĤ
    -0.06
    icio
    -0.06
    AXB
    -0.06
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.06
    ffa
    -0.06
    pert
    -0.06
    POSITIVE LOGITS
    :
    0.11
    utdown
    0.06
    ival
    0.06
    ा:
    0.06
    arden
    0.06
    taire
    0.06
    adam
    0.06
    830
    0.06
    :&
    0.06
    igit
    0.06
    Activations Density 0.011%

    No Known Activations