© 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. 88254
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases that indicate actions or obligations

    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
    áty
    -0.07
    hei
    -0.07
    reater
    -0.07
    \\\\
    -0.06
    ÑĨа
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    riors
    -0.06
    _REFER
    -0.06
    ãĥ³ãĥĩ
    -0.06
    rám
    -0.06
    POSITIVE LOGITS
    uppen
    0.07
    avid
    0.07
    ieber
    0.06
    icone
    0.06
    íĪ¬
    0.06
    _losses
    0.06
    ahren
    0.06
    OwnProperty
    0.05
    éric
    0.05
     Gal
    0.05
    Activations Density 0.058%

    No Known Activations