© 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. 57017
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their impacts on Jewish identity and culture

    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
     strr
    -0.06
    é³
    -0.05
     ElseIf
    -0.05
     xl
    -0.05
    484
    -0.05
    enge
    -0.05
     Huge
    -0.05
     lt
    -0.05
    agne
    -0.05
     GObject
    -0.05
    POSITIVE LOGITS
    IFF
    0.08
    ุà¸ļ
    0.08
    itan
    0.07
    IPAddress
    0.07
    vertime
    0.07
     physic
    0.07
    isContained
    0.07
    éϽ
    0.07
    verting
    0.07
    andles
    0.06
    Activations Density 0.151%

    No Known Activations