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

    Neuronpedia

    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. 119878
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or possibility, particularly those expressing actions or changes that can lead to different outcomes

    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
     componentDid
    -0.08
    unger
    -0.07
    aqu
    -0.07
    اسÙħ
    -0.07
    ÑĩаÑģно
    -0.07
    anca
    -0.07
    رÛĮÙĤ
    -0.07
    .ts
    -0.07
    TS
    -0.07
    asper
    -0.07
    POSITIVE LOGITS
     a
    0.08
     increased
    0.08
     greater
    0.08
     an
    0.08
     further
    0.07
     decreased
    0.07
     being
    0.07
    RuntimeObject
    0.06
     addCriterion
    0.06
     formation
    0.06
    Activations Density 0.027%

    No Known Activations