Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84217
    Prev
    Next
    INDEX
    Explanations

    quantities, particularly the number two and its variations in different 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
     couple
    -0.06
    iger
    -0.06
    (Pos
    -0.05
    ÑģÑĤи
    -0.05
    Ñħи
    -0.05
    ãĥ¼ãĥ¬
    -0.05
    beer
    -0.05
     Fame
    -0.05
     trio
    -0.05
    olar
    -0.05
    POSITIVE LOGITS
    gether
    0.09
    üzel
    0.08
     peas
    0.07
    ionario
    0.07
    ENTA
    0.07
     alike
    0.07
    ityEngine
    0.07
    OperationException
    0.07
     separate
    0.07
     तरफ
    0.07
    Activations Density 0.013%

    No Known Activations