© 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. 73142
    Prev
    Next
    INDEX
    Explanations

    highly negative or critical sentiments expressed in text

    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
    iel
    -0.07
    itor
    -0.06
    izar
    -0.06
    ubat
    -0.06
    IGO
    -0.06
    igo
    -0.06
    .)↵↵↵↵
    -0.06
    ãģ§ãģĤ
    -0.06
    人éĸĵ
    -0.06
    reve
    -0.05
    POSITIVE LOGITS
    /compiler
    0.07
    ouri
    0.07
    ehler
    0.06
     am
    0.06
    roperty
    0.06
    eyen
    0.06
     tiener
    0.06
    quier
    0.06
    andest
    0.06
     recruit
    0.06
    Activations Density 0.002%

    No Known Activations