© 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. 126807
    Prev
    Next
    INDEX
    Explanations

    specific cultural references and elements

    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
    ARN
    -0.07
     каÑģ
    -0.07
    ack
    -0.07
    tw
    -0.06
     addObserver
    -0.06
    547
    -0.06
    åĩĮ
    -0.06
    angs
    -0.05
    ões
    -0.05
    aced
    -0.05
    POSITIVE LOGITS
    íĨłíĨł
    0.07
     Insecta
    0.07
    ücken
    0.06
    ENTION
    0.06
     newPos
    0.06
    .***.***
    0.06
    leigh
    0.06
    raya
    0.06
    /Branch
    0.06
     Elemental
    0.06
    Activations Density 0.005%

    No Known Activations