© 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. 17628
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and individual experiences

    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
    usr
    -0.07
     KL
    -0.06
    oller
    -0.06
     Kr
    -0.06
     fact
    -0.06
     Cruz
    -0.05
    asic
    -0.05
    ãĥ¼ãĥ©
    -0.05
     stern
    -0.05
    _unregister
    -0.05
    POSITIVE LOGITS
    екÑĤи
    0.08
    fault
    0.08
    -prepend
    0.08
    ponsive
    0.08
     fault
    0.07
    _GENERIC
    0.07
    ¶Į
    0.07
    SENT
    0.07
    ÅĽ
    0.07
    ibal
    0.07
    Activations Density 0.027%

    No Known Activations