© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    phrases involving searching for or indexing user names

    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
    erea
    -0.06
    bite
    -0.06
    Äįas
    -0.06
    ENA
    -0.06
    berger
    -0.06
    etto
    -0.06
     AssemblyVersion
    -0.06
    еж
    -0.06
    CallCheck
    -0.06
    dda
    -0.06
    POSITIVE LOGITS
     name
    0.11
     Name
    0.08
     id
    0.07
    name
    0.07
     Id
    0.07
     NAME
    0.07
    riteria
    0.07
    _name
    0.07
    -name
    0.07
    åIJįåŃĹ
    0.07
    Activations Density 0.038%

    No Known Activations