© 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. 118578
    Prev
    Next
    INDEX
    Explanations

    phrases related to product information and reviews

    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
     Michele
    -0.06
    arel
    -0.06
     Sn
    -0.06
    atel
    -0.06
    tran
    -0.06
    apia
    -0.06
    art
    -0.06
    ı
    -0.05
    elman
    -0.05
    åĢŁ
    -0.05
    POSITIVE LOGITS
    ocz
    0.08
     product
    0.07
    edor
    0.07
    arness
    0.07
    ragen
    0.07
     reviews
    0.07
    ÑĢиÑĩ
    0.07
     stabilized
    0.07
    _reviews
    0.07
    cej
    0.06
    Activations Density 0.001%

    No Known Activations