© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118572
    Prev
    Next
    INDEX
    Explanations

    elements related to website or application structure

    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
     distr
    -0.06
     cep
    -0.06
    329
    -0.06
    OSE
    -0.05
    cep
    -0.05
     cease
    -0.05
     nam
    -0.05
    aign
    -0.05
    Å¡ka
    -0.05
    bose
    -0.05
    POSITIVE LOGITS
    ëı
    0.07
    enheim
    0.07
    (Encoding
    0.07
    uzz
    0.07
     Vent
    0.07
    isode
    0.07
    otor
    0.07
     Childhood
    0.07
    ìłij
    0.06
     content
    0.06
    Activations Density 0.028%

    No Known Activations