© 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. 9-LLAMASCOPE-RES-131K
    6. 95675
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to cardiovascular and urinary health

    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
    LEC
    -0.08
    uvre
    -0.07
    wahl
    -0.07
    otec
    -0.06
    uve
    -0.06
    533
    -0.06
    scri
    -0.06
    iola
    -0.06
    Operation
    -0.06
    pz
    -0.06
    POSITIVE LOGITS
     ==============================================================
    0.06
     Mud
    0.06
     Nielsen
    0.06
     unl
    0.06
    -setup
    0.06
     Kad
    0.06
     Franklin
    0.06
     Pes
    0.06
    κÏħ
    0.06
     Chad
    0.06
    Activations Density 0.010%

    No Known Activations