© 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. 26850
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activity and legal proceedings

    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
    _singleton
    -0.08
    ì°°
    -0.07
    InstanceState
    -0.07
    pta
    -0.07
    udit
    -0.07
    inkel
    -0.07
    rax
    -0.07
    olem
    -0.07
    antu
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
     helper
    0.07
     participation
    0.07
     Participation
    0.06
     Nar
    0.06
    åıĤä¸İ
    0.06
    icipation
    0.06
     abort
    0.06
    arness
    0.06
     Helper
    0.06
     åıĤ
    0.06
    Activations Density 0.018%

    No Known Activations