© 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. 71222
    Prev
    Next
    INDEX
    Explanations

    references to affiliate marketing and compensation structures

    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
    .scalablytyped
    -0.08
    alles
    -0.07
    weetalert
    -0.06
    neas
    -0.06
    anken
    -0.06
    allis
    -0.06
     |--------------------------------------------------------------------------↵
    -0.06
     اÙĦدÙĬÙĨ
    -0.06
    erty
    -0.05
    obia
    -0.05
    POSITIVE LOGITS
    .onPause
    0.07
     earn
    0.07
    icot
    0.07
    eyJ
    0.06
    icas
    0.06
    obot
    0.06
     Assertion
    0.06
    /ws
    0.06
    YLES
    0.06
    ç´Ģ
    0.06
    Activations Density 0.002%

    No Known Activations