© 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. 119376
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to economic and social risks

    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
    688
    -0.07
     Anc
    -0.06
     sometimes
    -0.06
    ardash
    -0.06
    quine
    -0.06
     meant
    -0.06
    esimal
    -0.06
     somewhat
    -0.06
    agas
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
     likely
    0.07
     Retro
    0.07
    lock
    0.07
    ieri
    0.06
    .opensource
    0.06
    esa
    0.06
     lock
    0.06
    лки
    0.06
     retro
    0.06
     liability
    0.06
    Activations Density 0.030%

    No Known Activations