© 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. 87596
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and state management in code

    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
    .Utc
    -0.08
    affle
    -0.07
    seau
    -0.07
    teen
    -0.07
    irsch
    -0.07
    uml
    -0.07
    antiago
    -0.07
    immel
    -0.07
    ÑĢÑĥж
    -0.07
    DidEnter
    -0.07
    POSITIVE LOGITS
     =
    0.08
    =null
    0.08
     gone
    0.07
    =None
    0.07
    .Dispose
    0.07
    ouns
    0.07
    apolis
    0.06
     Gone
    0.06
     sentence
    0.06
    =NULL
    0.06
    Activations Density 0.014%

    No Known Activations