© 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 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. 71174
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental destruction or damage

    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
     optionally
    -0.07
    icz
    -0.07
     Wyn
    -0.07
    allis
    -0.06
    лÑı
    -0.06
    avana
    -0.06
    un
    -0.06
    ucha
    -0.06
    atab
    -0.06
    cz
    -0.06
    POSITIVE LOGITS
    PCP
    0.07
     anale
    0.07
    ÑĮÑİÑĤ
    0.07
    CMP
    0.07
    ï¿¥
    0.07
    /stretch
    0.07
    nad
    0.07
    ãĢĶ
    0.06
    AGR
    0.06
    #echo
    0.06
    Activations Density 0.000%

    No Known Activations