© 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. 16783
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a service or offering, particularly in the context of assistance or consulting

    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
    isphere
    -0.07
    .vertx
    -0.07
    esco
    -0.07
    à¥įरव
    -0.07
    áng
    -0.06
    regon
    -0.06
    ÑĩÑĥк
    -0.06
    raid
    -0.06
    ÙĦÙĪد
    -0.06
    ²
    -0.06
    POSITIVE LOGITS
     vit
    0.07
     inc
    0.07
    ados
    0.06
     Vit
    0.06
    oku
    0.06
    avan
    0.06
    /Gate
    0.06
    ÑĢик
    0.06
     Ryder
    0.06
     disposed
    0.06
    Activations Density 0.001%

    No Known Activations