© 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. 78645
    Prev
    Next
    INDEX
    Explanations

    references to wildlife and its conservation

    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
    sect
    -0.08
    izu
    -0.07
    _REQUIRED
    -0.07
    oga
    -0.07
    ders
    -0.07
    ida
    -0.07
    åĪĩãĤĬ
    -0.07
    ater
    -0.07
    aurus
    -0.07
    steen
    -0.07
    POSITIVE LOGITS
    zimmer
    0.07
    bett
    0.07
    led
    0.06
    park
    0.06
    odge
    0.06
    ieten
    0.06
    urge
    0.06
     preserve
    0.06
    blood
    0.06
    ppe
    0.06
    Activations Density 0.005%

    No Known Activations