© 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. 9-LLAMASCOPE-RES-131K
    11. 98700
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or groups related to military and historical contexts

    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
    eldom
    -0.08
     Downs
    -0.07
     cry
    -0.06
    oop
    -0.06
    .sql
    -0.06
    ichten
    -0.06
     Caller
    -0.06
    çon
    -0.06
    wt
    -0.06
    oria
    -0.06
    POSITIVE LOGITS
    živ
    0.07
    bose
    0.07
    íĽĪ
    0.06
    èī
    0.06
     å¾ĴæŃ©
    0.06
    avenport
    0.06
    .sy
    0.06
    lamaz
    0.06
    PWD
    0.06
    baÅŁ
    0.06
    Activations Density 0.001%

    No Known Activations