© 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. 119916
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations labeled as "good ideas."

    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
    ogui
    -0.08
    ynn
    -0.08
    meldung
    -0.08
    ardash
    -0.08
     BeÅŁ
    -0.07
    pei
    -0.07
    orthand
    -0.07
    OUCH
    -0.07
    ussen
    -0.07
    indh
    -0.07
    POSITIVE LOGITS
    oins
    0.06
    kap
    0.06
    ubit
    0.06
     ince
    0.06
    349
    0.06
    inite
    0.05
    hay
    0.05
     keeps
    0.05
    -sm
    0.05
    oined
    0.05
    Activations Density 0.005%

    No Known Activations