© 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. 106394
    Prev
    Next
    INDEX
    Explanations

    words related to references or citations in academic or formal writing

    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
    acre
    -0.07
    izzato
    -0.07
    bara
    -0.07
    thers
    -0.07
     Till
    -0.07
    bridge
    -0.07
    brig
    -0.06
    aleza
    -0.06
    rete
    -0.06
     reprint
    -0.06
    POSITIVE LOGITS
    abl
    0.07
    ignKey
    0.07
    _pago
    0.07
    á»Ļt
    0.06
    MOTE
    0.06
    zione
    0.06
    Pago
    0.06
    ritt
    0.06
    DU
    0.06
    òi
    0.06
    Activations Density 0.028%

    No Known Activations