© 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. 5-LLAMASCOPE-RES-131K
    6. 125922
    Prev
    Next
    INDEX
    Explanations

    terms related to flood insurance

    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
    UILD
    -0.06
     fuel
    -0.06
     fuels
    -0.06
    Ñŀ
    -0.06
     refr
    -0.06
     branch
    -0.06
     ne
    -0.06
    .kotlin
    -0.06
     (
    -0.05
     Branch
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    å¿Ĺ
    0.07
    abox
    0.07
     Byl
    0.07
    ector
    0.07
    iams
    0.07
    erah
    0.07
    baum
    0.07
    .onNext
    0.07
    ague
    0.06
    Activations Density 0.001%

    No Known Activations