© 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. 5-LLAMASCOPE-RES-131K
    11. 125664
    Prev
    Next
    INDEX
    Explanations

    references to bed and breakfast accommodations

    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
    hind
    -0.06
     æ¬
    -0.06
    ious
    -0.06
    opa
    -0.06
    lei
    -0.06
    itzer
    -0.05
    ippi
    -0.05
    shine
    -0.05
     plain
    -0.05
    ÅĤe
    -0.05
    POSITIVE LOGITS
    zilla
    0.07
     Morm
    0.07
    Injector
    0.07
    BOOT
    0.07
    £i
    0.07
    £¼
    0.07
    _regs
    0.06
    _SLAVE
    0.06
    sWith
    0.06
    ampton
    0.06
    Activations Density 0.004%

    No Known Activations