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

    Neuronpedia

    Jacobian LensNEW
    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. 88162
    Prev
    Next
    INDEX
    Explanations

    references to Android development components and functions

    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
    .scalablytyped
    -0.09
    strand
    -0.07
    .IsNullOr
    -0.07
    ailles
    -0.07
    ÅĪ
    -0.07
    .ali
    -0.07
    orsch
    -0.06
    lodash
    -0.06
    onder
    -0.06
    ady
    -0.06
    POSITIVE LOGITS
    ammen
    0.06
    ABS
    0.06
    íĿ
    0.06
    376
    0.06
    373
    0.06
    457
    0.06
    ixin
    0.06
    381
    0.06
    517
    0.05
     Robertson
    0.05
    Activations Density 0.000%

    No Known Activations