© 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. 90241
    Prev
    Next
    INDEX
    Explanations

    concepts related to autonomy and self-determination within various contexts

    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
    eria
    -0.07
    LM
    -0.06
     overnight
    -0.06
     Gri
    -0.06
    916
    -0.06
    uji
    -0.06
     Dart
    -0.06
    lander
    -0.05
    à¸Īำ
    -0.05
    .cy
    -0.05
    POSITIVE LOGITS
     control
    0.12
    control
    0.11
     freedom
    0.11
     Control
    0.10
    Control
    0.10
     CHO
    0.10
    -control
    0.10
    Independ
    0.10
     sovereignty
    0.10
    fre
    0.10
    Activations Density 0.141%

    No Known Activations