© 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. 78465
    Prev
    Next
    INDEX
    Explanations

    the verb "take" in various forms and contexts

    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
    mun
    -0.06
    rij
    -0.06
    andon
    -0.06
    rom
    -0.06
    ime
    -0.06
    pus
    -0.06
    ri
    -0.06
    /we
    -0.06
    rika
    -0.06
    nu
    -0.06
    POSITIVE LOGITS
     advantage
    0.14
    aways
    0.10
    uchi
    0.08
     ÑĥÑĩаÑģÑĤÑĮ
    0.08
    htag
    0.08
     risks
    0.08
     refuge
    0.08
     responsibility
    0.08
     pride
    0.08
     advant
    0.07
    Activations Density 0.090%

    No Known Activations