© 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. 1047
    Prev
    Next
    INDEX
    Explanations

    legal and legislative reforms

    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
    emiz
    -0.07
    abbr
    -0.07
    okane
    -0.07
     VÅ¡ech
    -0.07
    ovnÃŃ
    -0.07
    abant
    -0.07
    ippo
    -0.07
    ãģ«ãģĬ
    -0.07
     INTERRUPTION
    -0.06
    lsa
    -0.06
    POSITIVE LOGITS
    ILLA
    0.07
    åħģ
    0.06
    PILE
    0.06
     allowed
    0.06
    illa
    0.06
     Ñĥж
    0.06
     allows
    0.06
     permanent
    0.05
    ât
    0.05
     Prim
    0.05
    Activations Density 0.025%

    No Known Activations