© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85143
    Prev
    Next
    INDEX
    Explanations

    mentions of hierarchical ranking or categorization in various contexts

    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
    èľľ
    -0.07
    andle
    -0.07
    orias
    -0.07
    orex
    -0.06
    STA
    -0.06
    oral
    -0.06
    ledo
    -0.06
     grav
    -0.06
    ongan
    -0.06
    reuse
    -0.06
    POSITIVE LOGITS
    endant
    0.06
     remaining
    0.06
    etta
    0.06
    æ±
    0.06
     Garc
    0.06
    ãĥĶãĥ¼
    0.06
    fect
    0.06
    verture
    0.06
    iri
    0.06
     Cliff
    0.06
    Activations Density 0.014%

    No Known Activations