© 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. 15-LLAMASCOPE-RES-131K
    6. 27194
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to navigation and user interface controls

    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
    vyk
    -0.08
    itti
    -0.08
    ocity
    -0.08
    contres
    -0.07
    lify
    -0.07
    dsl
    -0.07
    ..↵↵↵↵
    -0.07
    inez
    -0.07
    ocities
    -0.07
    LOOP
    -0.07
    POSITIVE LOGITS
     Christoph
    0.07
     Clare
    0.06
    za
    0.05
    andler
    0.05
     Ple
    0.05
     BRA
    0.05
     tro
    0.05
     explicit
    0.05
     Hollande
    0.05
     Ridley
    0.05
    Activations Density 0.000%

    No Known Activations