© 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. 125406
    Prev
    Next
    INDEX
    Explanations

    terms associated with professional and academic qualifications

    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
    íģ¼
    -0.08
    EXPR
    -0.08
    oho
    -0.07
     Ekon
    -0.07
    سÛĮÙĨ
    -0.07
    eto
    -0.07
    stride
    -0.07
     æ¾
    -0.07
    ft
    -0.07
    _Il
    -0.07
    POSITIVE LOGITS
    imensional
    0.06
    482
    0.06
    ibu
    0.06
    acent
    0.06
    ificates
    0.06
    sla
    0.05
     {{{
    0.05
    alty
    0.05
     Kirby
    0.05
    ethyst
    0.05
    Activations Density 0.128%

    No Known Activations