© 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. 17220
    Prev
    Next
    INDEX
    Explanations

    arguments that challenge established scientific assumptions and critiques of mainstream views

    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
    è¼Ķ
    -0.07
    ÙĪÙĨا
    -0.06
     пеÑĢеп
    -0.06
    podob
    -0.06
    yyy
    -0.06
     Devils
    -0.06
    bben
    -0.06
    SSL
    -0.06
    XXXX
    -0.06
    cms
    -0.06
    POSITIVE LOGITS
     conventional
    0.09
     Linear
    0.08
     simplistic
    0.07
     linear
    0.07
    ati
    0.07
     assumptions
    0.07
    popular
    0.07
    CHED
    0.07
    ories
    0.07
     mainstream
    0.06
    Activations Density 0.043%

    No Known Activations