© 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. 15-LLAMASCOPE-RES-131K
    11. 61627
    Prev
    Next
    INDEX
    Explanations

    references to legal or technical document 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
    id
    -0.06
    áºŃu
    -0.06
    ]
    -0.06
    oola
    -0.06
    ”
    -0.06
    ijd
    -0.06
     Salem
    -0.06
    it
    -0.05
    ash
    -0.05
    &
    -0.05
    POSITIVE LOGITS
    oftware
    0.08
    ή
    0.08
    #ab
    0.08
    à¹ij
    0.08
    ến
    0.08
    @brief
    0.08
    Sharper
    0.08
    BarItem
    0.07
    hetto
    0.07
     å¾ĴæŃ©
    0.07
    Activations Density 0.103%

    No Known Activations