© 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. 29504
    Prev
    Next
    INDEX
    Explanations

    concepts related to collaboration and partnerships within organizations

    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
    yi
    -0.08
     Rencontres
    -0.07
    plet
    -0.07
    ãĥ¥ãĥ¼
    -0.07
    å¨
    -0.07
    udio
    -0.06
     رÙĤ
    -0.06
    zin
    -0.06
    aph
    -0.06
    寺
    -0.06
    POSITIVE LOGITS
     partner
    0.12
     partners
    0.10
     others
    0.10
    partner
    0.10
     outs
    0.10
     Partner
    0.09
     extern
    0.09
     contracted
    0.08
     external
    0.08
     Others
    0.08
    Activations Density 0.030%

    No Known Activations