© 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. 90167
    Prev
    Next
    INDEX
    Explanations

    nouns and specific entities related to various subjects and contexts

    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
    cke
    -0.08
     queryInterface
    -0.07
     pinch
    -0.07
    cela
    -0.07
    rita
    -0.07
    legg
    -0.07
    ุà¸Ķà¸Ĺ
    -0.07
    arga
    -0.07
    Ñīин
    -0.07
    boom
    -0.07
    POSITIVE LOGITS
     Synd
    0.07
    undo
    0.06
     syndrome
    0.06
    utschein
    0.06
     Middleton
    0.06
     synd
    0.06
     approach
    0.05
     Eric
    0.05
     Syndrome
    0.05
     Bord
    0.05
    Activations Density 0.266%

    No Known Activations