© 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. 128637
    Prev
    Next
    INDEX
    Explanations

    phrases related to sequences or repetitions

    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
    amac
    -0.08
    ebek
    -0.08
    ofire
    -0.07
     assort
    -0.07
     desar
    -0.07
    Traversal
    -0.07
    _firestore
    -0.07
    -syntax
    -0.07
    __$
    -0.07
    ιÏĥÏĦο
    -0.07
    POSITIVE LOGITS
     steps
    0.08
     consecutive
    0.06
     posts
    0.06
     events
    0.06
    ì¹
    0.06
     interconnected
    0.06
     three
    0.06
    yan
    0.06
    pos
    0.06
     rapid
    0.06
    Activations Density 0.013%

    No Known Activations