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

    Neuronpedia

    Jacobian LensNEW
    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. 75086
    Prev
    Next
    INDEX
    Explanations

    affirmations or statements of existence

    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
     ponto
    -0.06
    these
    -0.06
    led
    -0.06
    anco
    -0.06
     bestimm
    -0.06
    umbo
    -0.06
     Ple
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
    _CALLBACK
    -0.06
    er
    -0.06
    POSITIVE LOGITS
    eki
    0.08
    ecut
    0.07
     how
    0.07
     footage
    0.07
     Dock
    0.07
    iph
    0.07
    Minus
    0.07
     information
    0.06
    ãĥ³ãĤ¿
    0.06
     advice
    0.06
    Activations Density 0.011%

    No Known Activations