© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    references to human rights policies and frameworks

    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
    oje
    -0.06
    baugh
    -0.06
     MediaTek
    -0.06
    ensa
    -0.06
    ány
    -0.06
    anova
    -0.05
     Rural
    -0.05
    orex
    -0.05
     bef
    -0.05
     dzie
    -0.05
    POSITIVE LOGITS
    icast
    0.08
     prom
    0.08
    eus
    0.08
    ılıç
    0.08
    prom
    0.07
    explicit
    0.07
    _lazy
    0.07
    RIPT
    0.07
    GLOBALS
    0.07
     mand
    0.07
    Activations Density 0.031%

    No Known Activations