© 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. 93993
    Prev
    Next
    INDEX
    Explanations

    collaborative or related terms concerning interpersonal connections and relationships

    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
    razil
    -0.09
    LOPT
    -0.08
    URLException
    -0.08
    porto
    -0.08
    ystack
    -0.07
    bstract
    -0.07
    dna
    -0.07
    stash
    -0.07
    lexport
    -0.07
    ¯ÃĤ
    -0.07
    POSITIVE LOGITS
     colleagues
    0.07
    579
    0.06
     counterparts
    0.06
     fellow
    0.06
     partner
    0.06
     counterpart
    0.06
     partners
    0.06
     coun
    0.06
    515
    0.06
     colleague
    0.06
    Activations Density 0.020%

    No Known Activations