© 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 EvalsExportsinterp-engineNEWAPI 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. 104490
    Prev
    Next
    INDEX
    Explanations

    terms related to particle physics and nuclear structures

    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
    fak
    -0.08
    	explicit
    -0.06
    @show
    -0.06
    /cms
    -0.06
    harma
    -0.06
     IDirect
    -0.06
    duk
    -0.06
    IPS
    -0.06
    eltas
    -0.06
     à¤Ńर
    -0.06
    POSITIVE LOGITS
    ilha
    0.07
    ombre
    0.07
    å±ħ
    0.07
    azu
    0.07
    óc
    0.06
    -dominated
    0.06
    ainless
    0.06
    GENCY
    0.06
    etag
    0.06
     field
    0.06
    Activations Density 0.073%

    No Known Activations