© 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 EvalsExportsinterp-engineNEWAPI 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. 123980
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be"

    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
     Dep
    -0.06
    inton
    -0.06
    ond
    -0.06
    ĶĶ
    -0.06
    ure
    -0.06
    åĽ£
    -0.06
    r
    -0.05
     strongly
    -0.05
     wig
    -0.05
    É
    -0.05
    POSITIVE LOGITS
    ê¼
    0.08
    cisi
    0.08
     ëĦ¤ìĿ´íĬ¸
    0.07
    appropriate
    0.07
    ValuePair
    0.07
    iaux
    0.07
    ÑĤÑĮ
    0.07
    .scalablytyped
    0.07
    berger
    0.07
    Ĵáŀ
    0.07
    Activations Density 0.010%

    No Known Activations