© 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. 29-LLAMASCOPE-RES-32K
    11. 18775
    Prev
    Next
    INDEX
    Explanations

    references to loyalty or love-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nicol
    -0.14
    PT
    -0.14
    adu
    -0.14
    lice
    -0.14
    844
    -0.14
    aná
    -0.14
    ëħIJ
    -0.13
     damer
    -0.13
    ubyte
    -0.13
    _stderr
    -0.13
    POSITIVE LOGITS
    seau
    0.18
    eliness
    0.18
    icrous
    0.18
    ely
    0.17
    alty
    0.17
    /lo
    0.17
    lei
    0.17
    ullo
    0.17
    elly
    0.17
    енз
    0.16
    Activations Density 0.019%

    No Known Activations