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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119392
    Prev
    Next
    INDEX
    Explanations

    past tense verbs that indicate actions or events

    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
    -Origin
    -0.06
     lam
    -0.06
    intColor
    -0.06
     rip
    -0.05
    onas
    -0.05
     later
    -0.05
    ãĥ£
    -0.05
     additional
    -0.05
    _delegate
    -0.05
    arge
    -0.05
    POSITIVE LOGITS
     located
    0.07
    aget
    0.07
    inand
    0.07
    izik
    0.07
    ãĤ¤ãĤº
    0.07
    usters
    0.06
    located
    0.06
    важ
    0.06
     situated
    0.06
     desn
    0.06
    Activations Density 0.037%

    No Known Activations