© 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. 83989
    Prev
    Next
    INDEX
    Explanations

    phrases related to food and dining experiences

    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
    èĸĦ
    -0.07
    ÛĮدÛĮ
    -0.07
    Liver
    -0.07
    innie
    -0.07
    ennie
    -0.07
    .hadoop
    -0.06
     Appalach
    -0.06
     Annunci
    -0.06
    orny
    -0.06
     Liver
    -0.06
    POSITIVE LOGITS
     chiropr
    0.10
    iropr
    0.08
     verte
    0.08
     spinal
    0.07
    )did
    0.07
    iev
    0.06
    /LICENSE
    0.06
     alignments
    0.06
    -align
    0.06
     hol
    0.06
    Activations Density 0.005%

    No Known Activations