© 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. 77690
    Prev
    Next
    INDEX
    Explanations

    elements related to ethical considerations and decision-making processes

    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
     nrw
    -0.06
     lul
    -0.06
    ColumnInfo
    -0.06
    ίνη
    -0.06
    monic
    -0.06
    缣
    -0.06
    âu
    -0.06
    stein
    -0.06
    ẩu
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
    imal
    0.07
    iden
    0.07
    etten
    0.07
     Wend
    0.06
     rad
    0.06
     hol
    0.06
     Kata
    0.06
    uffle
    0.06
    342
    0.06
    ãĥ¼ãĤ¯
    0.06
    Activations Density 0.010%

    No Known Activations