© 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. 15-LLAMASCOPE-RES-131K
    11. 104052
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence and philosophical attributes

    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
    roud
    -0.08
    agos
    -0.07
     sur
    -0.07
    issen
    -0.07
    artz
    -0.07
    olu
    -0.07
    metis
    -0.06
    artin
    -0.06
    reinterpret
    -0.06
    arry
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤº
    0.06
    Scrollbar
    0.06
     intr
    0.06
     Charm
    0.06
    ardown
    0.06
    (thing
    0.06
    uvian
    0.06
     superv
    0.06
    _INTERNAL
    0.06
    /Area
    0.06
    Activations Density 0.000%

    No Known Activations