© 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. 84644
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to personal grooming and maintenance

    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
    hin
    -0.08
    ãĥªãĥ¼ãĤº
    -0.07
    ISTRIBUT
    -0.07
    çĤ®
    -0.07
    SSIP
    -0.07
    -widgets
    -0.07
    wart
    -0.07
    -sdk
    -0.07
    prar
    -0.06
    blast
    -0.06
    POSITIVE LOGITS
    arth
    0.06
    bjerg
    0.06
    owa
    0.06
     mell
    0.06
     Archae
    0.06
     HQ
    0.06
    oire
    0.06
     daily
    0.05
     fl
    0.05
     intr
    0.05
    Activations Density 0.000%

    No Known Activations