© 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. 16196
    Prev
    Next
    INDEX
    Explanations

    elements related to planning and arrangement

    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
    elin
    -0.07
    warts
    -0.07
    ucci
    -0.07
    reur
    -0.06
    ndl
    -0.06
    ÑĨе
    -0.06
    467
    -0.06
     Nun
    -0.06
    coni
    -0.06
     rarely
    -0.05
    POSITIVE LOGITS
     similar
    0.33
    similar
    0.26
     Similar
    0.25
    Similar
    0.24
     simil
    0.23
     benzer
    0.23
     similarly
    0.22
     podob
    0.21
    imilar
    0.20
     identical
    0.20
    Activations Density 0.101%

    No Known Activations