© 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. 15-LLAMASCOPE-RES-131K
    11. 1356
    Prev
    Next
    INDEX
    Explanations

    references to struggle and support within familial or community contexts

    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
     Osman
    -0.07
     outs
    -0.06
    importe
    -0.06
    OTS
    -0.06
    orp
    -0.06
    cad
    -0.06
    ellas
    -0.06
    yš
    -0.06
    MBER
    -0.06
    probe
    -0.06
    POSITIVE LOGITS
    acha
    0.08
    egan
    0.08
    ĴĮ
    0.07
    ephy
    0.06
    tgl
    0.06
    æķµ
    0.06
    argo
    0.06
    ác
    0.06
    spb
    0.06
    воÑĢ
    0.06
    Activations Density 0.031%

    No Known Activations