© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94035
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to experiments

    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
    seg
    -0.07
    248
    -0.06
    /maps
    -0.06
    ugal
    -0.06
     Fowler
    -0.06
    owler
    -0.06
    545
    -0.06
    706
    -0.06
    è¥
    -0.05
    HashTable
    -0.05
    POSITIVE LOGITS
     animal
    0.11
     humane
    0.11
    animal
    0.10
    Animal
    0.10
     Animal
    0.10
     animals
    0.10
     cruelty
    0.10
     euth
    0.09
    animals
    0.09
     Animalia
    0.08
    Activations Density 0.001%

    No Known Activations