© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106340
    Prev
    Next
    INDEX
    Explanations

    terms related to lottery and secure online practices

    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
    ãĥ³ãĥIJ
    -0.08
    @js
    -0.07
    é«ĺæ¸ħ
    -0.07
    leanor
    -0.07
    dni
    -0.07
    ledon
    -0.07
    .Fore
    -0.07
    WARE
    -0.07
    ãģĹãĤĩãģĨ
    -0.07
    /*@
    -0.07
    POSITIVE LOGITS
    heel
    0.07
    ä½³
    0.06
    apus
    0.06
    antis
    0.06
     Fusion
    0.06
    arat
    0.05
    mom
    0.05
    0.05
    acity
    0.05
    eced
    0.05
    Activations Density 0.007%

    No Known Activations