© 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. 17-LLAMASCOPE-RES-131K
    6. 77500
    Prev
    Next
    INDEX
    Explanations

    terms related to vaccination and medical conditions

    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
    ói
    -0.09
    oland
    -0.08
    gom
    -0.08
    olit
    -0.08
    jerne
    -0.08
    ebek
    -0.07
    ROID
    -0.07
    terra
    -0.07
    ION
    -0.07
    ůst
    -0.07
    POSITIVE LOGITS
     unable
    0.06
     themselves
    0.05
    aptic
    0.05
     status
    0.05
     sorted
    0.05
     yourselves
    0.05
    68
    0.05
     halde
    0.05
     reconc
    0.05
     deriving
    0.05
    Activations Density 0.028%

    No Known Activations