© 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. 17-LLAMASCOPE-RES-131K
    11. 126395
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic phase transitions and self-consistency in physical systems

    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
    linger
    -0.06
     Synthetic
    -0.06
     standardized
    -0.06
     ÑĢаз
    -0.06
    Sharp
    -0.06
     поÑģÑĤÑĥп
    -0.06
    essel
    -0.06
     Gos
    -0.06
    sortable
    -0.06
    verte
    -0.06
    POSITIVE LOGITS
     phase
    0.09
     transitions
    0.08
     phases
    0.08
     regime
    0.08
     transition
    0.07
     state
    0.07
     states
    0.07
     áll
    0.07
     regimes
    0.07
    azer
    0.07
    Activations Density 0.027%

    No Known Activations