© 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. 87435
    Prev
    Next
    INDEX
    Explanations

    phrases relating to guidance and support for setting up childcare services

    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
    ofire
    -0.08
    oting
    -0.08
    vier
    -0.07
    à¥Ĥद
    -0.07
    umn
    -0.07
    offsetof
    -0.07
    avian
    -0.07
    ãĥĪãĥ«
    -0.07
    нин
    -0.06
    ãĥªãĥ³ãĤ°
    -0.06
    POSITIVE LOGITS
    ellido
    0.07
     plus
    0.06
     result
    0.06
    -cols
    0.06
     they
    0.06
    ango
    0.06
    vere
    0.06
    mere
    0.06
    plus
    0.06
    FFFFFFFF
    0.06
    Activations Density 0.025%

    No Known Activations