Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29292
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to mental health and neurochemistry

    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
    _DEPRECATED
    -0.07
     Gund
    -0.06
    ffen
    -0.06
    ox
    -0.06
    ekl
    -0.06
    opes
    -0.06
    IMUM
    -0.06
    iste
    -0.06
    VOKE
    -0.06
    ansa
    -0.06
    POSITIVE LOGITS
     responsible
    0.09
    .scalablytyped
    0.08
     essential
    0.07
     InitializeComponent
    0.07
    ponsible
    0.07
     Responsible
    0.07
     plays
    0.07
     tÃŃn
    0.06
     inher
    0.06
    pins
    0.06
    Activations Density 0.015%

    No Known Activations