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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5106
    Prev
    Next
    INDEX
    Explanations

    discussions of arguments and theoretical concepts

    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
    arella
    -0.08
    iddy
    -0.07
     cins
    -0.07
    eydi
    -0.07
    annis
    -0.07
    ç¿Ķ
    -0.07
    ElementException
    -0.06
    ismo
    -0.06
    orthand
    -0.06
    ÑĥÑģа
    -0.06
    POSITIVE LOGITS
     Law
    0.09
     Rule
    0.09
     famous
    0.09
     Principle
    0.09
     law
    0.09
     infamous
    0.08
     famed
    0.08
     sunk
    0.08
     Reverse
    0.07
     principle
    0.07
    Activations Density 0.114%

    No Known Activations