© 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. 106088
    Prev
    Next
    INDEX
    Explanations

    elements related to social interactions and complex human 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
    icense
    -0.09
    anax
    -0.08
    cente
    -0.07
    ekk
    -0.07
    amil
    -0.07
     doma
    -0.07
    ependency
    -0.07
    ewire
    -0.07
    меÑĩ
    -0.07
    vrd
    -0.07
    POSITIVE LOGITS
     elim
    0.06
    ger
    0.06
    _rules
    0.06
    ì¹Ļ
    0.06
     rules
    0.06
     designated
    0.06
    ling
    0.06
     rounds
    0.06
     target
    0.06
     person
    0.05
    Activations Density 0.002%

    No Known Activations