© 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. 128346
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the act of weakening or damaging trust or stability

    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
    AZE
    -0.07
    ãĥ¼ãĥĭ
    -0.07
    ãĥ«ãĥķ
    -0.07
    inou
    -0.07
    izr
    -0.07
     Grü
    -0.07
    zd
    -0.07
    à¥Įड
    -0.07
    ìĹ´
    -0.07
    -INF
    -0.07
    POSITIVE LOGITS
     efforts
    0.09
     attempts
    0.08
     effort
    0.08
    /in
    0.07
     confidence
    0.07
    ling
    0.07
    0.07
     tim
    0.07
    /null
    0.06
    579
    0.06
    Activations Density 0.004%

    No Known Activations