© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1368
    Prev
    Next
    INDEX
    Explanations

    terms related to locality and position in context

    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
    _regeneration
    -0.09
    GenerationStrategy
    -0.09
    .localization
    -0.09
    ephir
    -0.08
    âĢĮاÙĨ
    -0.08
    ourke
    -0.08
    _Tis
    -0.08
    ¶ģ
    -0.08
    OffsetTable
    -0.08
    quirer
    -0.08
    POSITIVE LOGITS
    0.05
     conserv
    0.05
     br
    0.05
     #
    0.05
    ÑĢоÑģ
    0.05
     mobil
    0.05
     Spencer
    0.05
     prot
    0.05
     extra
    0.05
     sensation
    0.05
    Activations Density 0.075%

    No Known Activations