© 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. 84650
    Prev
    Next
    INDEX
    Explanations

    titles and entitled works or documents

    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
    etri
    -0.07
    _PHP
    -0.07
    Intialized
    -0.07
    deaux
    -0.07
    .www
    -0.07
     ******************************************************************************↵
    -0.07
    .Edit
    -0.06
    istrovstvÃŃ
    -0.06
    füg
    -0.06
    elta
    -0.06
    POSITIVE LOGITS
     titled
    0.10
     entitled
    0.10
     `
    0.07
     "
    0.07
    isci
    0.06
     _
    0.06
    uida
    0.06
    itled
    0.06
    lined
    0.06
    _<
    0.06
    Activations Density 0.032%

    No Known Activations