© 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. 17-LLAMASCOPE-RES-131K
    11. 130499
    Prev
    Next
    INDEX
    Explanations

    mentions of different tier levels and their corresponding characteristics or features

    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
    s
    -0.07
    ynth
    -0.07
    tion
    -0.07
    anh
    -0.06
    kker
    -0.06
     Aid
    -0.06
    zion
    -0.06
     STRICT
    -0.06
    t
    -0.06
     Stout
    -0.06
    POSITIVE LOGITS
    edList
    0.10
    ed
    0.10
    edImage
    0.10
    次
    0.09
    åĪ¥
    0.08
    级
    0.08
    ing
    0.07
    iffs
    0.07
    -level
    0.07
    edn
    0.07
    Activations Density 0.003%

    No Known Activations