© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74516
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of placing or positioning something

    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
    754
    -0.07
     klu
    -0.06
    atti
    -0.06
    /from
    -0.06
    avail
    -0.06
    813
    -0.06
    ata
    -0.06
    ppe
    -0.06
    /out
    -0.06
    ancement
    -0.06
    POSITIVE LOGITS
     emphasis
    0.10
    cala
    0.09
     bets
    0.09
    emphasis
    0.08
    tin
    0.08
     placed
    0.08
     blame
    0.07
    Limits
    0.07
    HOLDER
    0.07
    Segoe
    0.07
    Activations Density 0.015%

    No Known Activations