© 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. 57713
    Prev
    Next
    INDEX
    Explanations

    references to conflict and struggle

    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
    fty
    -0.07
    DCALL
    -0.07
    andise
    -0.07
    esco
    -0.06
    baugh
    -0.06
    alfa
    -0.06
    ursed
    -0.06
    Ñģен
    -0.06
    ãģ¡ãģ¯
    -0.06
    ANC
    -0.06
    POSITIVE LOGITS
    roit
    0.07
     Sele
    0.07
    -wall
    0.07
     å£
    0.07
     rev
    0.06
    çĥ
    0.06
     BCHP
    0.06
     Ell
    0.06
    reu
    0.06
    onym
    0.06
    Activations Density 0.001%

    No Known Activations