© 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. 647
    Prev
    Next
    INDEX
    Explanations

    instances of risk and strategy, particularly in contexts related to pursuit and conflict

    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
    odyn
    -0.08
    .scalablytyped
    -0.07
    osit
    -0.07
    odate
    -0.07
     moduleId
    -0.07
    izik
    -0.07
    /assert
    -0.07
    iram
    -0.07
     INTERRUPTION
    -0.07
    beros
    -0.07
    POSITIVE LOGITS
    arkin
    0.07
     unsus
    0.06
     obliged
    0.06
     betray
    0.06
     m
    0.06
    Vect
    0.06
     sooner
    0.06
     susceptible
    0.06
    alia
    0.06
     trying
    0.05
    Activations Density 0.092%

    No Known Activations