© 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. 83288
    Prev
    Next
    INDEX
    Explanations

    references to specific mathematical cases, concepts, and conditions within theoretical analysis

    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
    nick
    -0.07
    adam
    -0.06
    ä¸Ī
    -0.06
    jer
    -0.06
    aira
    -0.06
    adan
    -0.06
    yer
    -0.05
    pac
    -0.05
    vi
    -0.05
    AMA
    -0.05
    POSITIVE LOGITS
     case
    0.28
     cases
    0.24
    case
    0.22
     Case
    0.21
     Cases
    0.20
     caso
    0.20
    Case
    0.20
    cases
    0.19
    -case
    0.18
    	case
    0.17
    Activations Density 0.291%

    No Known Activations