© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    references to life events such as birth and death

    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
    знаÑĩа
    -0.08
    æĨ
    -0.07
    ç§
    -0.07
    [$_
    -0.07
    otics
    -0.06
    rech
    -0.06
    ACP
    -0.06
     GÃľ
    -0.06
    .isNullOrEmpty
    -0.06
    unsch
    -0.06
    POSITIVE LOGITS
     Hop
    0.06
    uell
    0.06
    lund
    0.06
    ikler
    0.05
    ona
    0.05
    ë³´
    0.05
    γον
    0.05
    eras
    0.05
     Greene
    0.05
    баÑĩ
    0.05
    Activations Density 0.000%

    No Known Activations