© 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. 130590
    Prev
    Next
    INDEX
    Explanations

    specific postal codes and addresses

    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
    772
    -0.06
    ypy
    -0.06
    riends
    -0.06
     Dude
    -0.06
    4
    -0.06
    lander
    -0.06
    assa
    -0.06
    746
    -0.06
    ible
    -0.06
     inflation
    -0.05
    POSITIVE LOGITS
    _FT
    0.07
    ãĥıãĤ¤
    0.07
     cob
    0.06
     Stein
    0.06
    ogne
    0.06
    å¾ĴæŃ©
    0.06
     PROFITS
    0.06
    enco
    0.06
     à¤īल
    0.06
     giao
    0.06
    Activations Density 0.005%

    No Known Activations