© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106153
    Prev
    Next
    INDEX
    Explanations

    phrases related to product reviews or evaluations

    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
    âĢ¦↵↵
    -0.06
     Ket
    -0.06
     wikipedia
    -0.06
    qty
    -0.06
    .lv
    -0.06
     âĢ¦↵↵
    -0.06
    âĢ¦↵
    -0.06
     Wikipedia
    -0.05
     ens
    -0.05
    ALAR
    -0.05
    POSITIVE LOGITS
    EXTERN
    0.08
    cht
    0.08
    indre
    0.08
    andr
    0.07
    ktop
    0.07
    зн
    0.07
    FFE
    0.07
    uesday
    0.07
     column
    0.07
    efa
    0.07
    Activations Density 0.053%

    No Known Activations