© 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. 56535
    Prev
    Next
    INDEX
    Explanations

    words beginning with the letter 'W'

    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
    eer
    -0.09
    oint
    -0.07
    olf
    -0.07
    idget
    -0.07
    rapper
    -0.07
    ease
    -0.07
    éĢ£
    -0.06
    ugins
    -0.06
    InstanceOf
    -0.06
    yssey
    -0.06
    POSITIVE LOGITS
    amel
    0.07
     quoi
    0.07
    SSIP
    0.07
     ur
    0.06
    kin
    0.06
     broad
    0.06
    ikon
    0.06
    pedo
    0.06
    ilm
    0.06
    amac
    0.06
    Activations Density 0.036%

    No Known Activations