© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40808
    Prev
    Next
    INDEX
    Explanations

    instances of the word "revisit" and its variations related to reconsideration or reflection on past topics

    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
    /lic
    -0.08
    наÑĢÑĥж
    -0.08
    ãĤĦãĤĭ
    -0.08
    лоÑĤ
    -0.08
    ekl
    -0.08
    iedades
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
     ÄĮech
    -0.07
    edom
    -0.07
    .Sdk
    -0.07
    POSITIVE LOGITS
     old
    0.08
     concept
    0.07
     themes
    0.07
    usan
    0.07
    æĹ§
    0.07
     earlier
    0.06
     familiar
    0.06
    ple
    0.06
    orig
    0.06
     former
    0.06
    Activations Density 0.012%

    No Known Activations