© 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. 16050
    Prev
    Next
    INDEX
    Explanations

    language related to break-ins or forced entries

    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
     Ire
    -0.07
    obble
    -0.07
    olleyError
    -0.07
    istrovstvÃŃ
    -0.07
     drib
    -0.07
    ayment
    -0.07
     uphill
    -0.07
    uet
    -0.07
    amburger
    -0.06
    ısıt
    -0.06
    POSITIVE LOGITS
     access
    0.06
     panel
    0.06
     window
    0.06
     bypass
    0.06
     latch
    0.06
     Shore
    0.06
     Cle
    0.06
     Access
    0.06
     Suff
    0.06
     vegetation
    0.06
    Activations Density 0.010%

    No Known Activations