© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3381
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and conflicts

    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
    orio
    -0.08
    tridges
    -0.08
    oir
    -0.08
    alars
    -0.08
    ouro
    -0.08
    неÑĢг
    -0.08
    ibri
    -0.07
    ãĤ¹ãĤ³
    -0.07
    typeorm
    -0.07
    iento
    -0.07
    POSITIVE LOGITS
    udy
    0.07
     Baby
    0.06
     Paid
    0.06
     Allied
    0.06
     Game
    0.06
     Burgess
    0.06
     Superior
    0.06
     Pluto
    0.05
     stagn
    0.05
    illis
    0.05
    Activations Density 0.001%

    No Known Activations