© 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. 29146
    Prev
    Next
    INDEX
    Explanations

    addresses or location information

    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
    eras
    -0.07
    _ber
    -0.07
    ber
    -0.07
     Carp
    -0.06
    jec
    -0.06
    chat
    -0.06
    aber
    -0.06
    éģĭ
    -0.06
    icients
    -0.06
    alk
    -0.06
    POSITIVE LOGITS
    Suite
    0.11
     Suite
    0.10
     suite
    0.09
    suite
    0.09
     office
    0.09
     offices
    0.08
    åĬŀåħ¬
    0.08
    office
    0.07
    ุà¸ķ
    0.06
    ì¦Į
    0.06
    Activations Density 0.010%

    No Known Activations