© 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. 14-LLAMASCOPE-RES-32K
    11. 30608
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hoard" and associated terms related to excessive accumulation or obsession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ro
    -0.22
    nya
    -0.20
    ka
    -0.20
    ling
    -0.19
    ness
    -0.19
    no
    -0.19
    ne
    -0.19
    mente
    -0.18
    ten
    -0.17
    li
    -0.17
    POSITIVE LOGITS
    strand
    0.17
    oji
    0.17
    imat
    0.16
    enk
    0.15
    zen
    0.15
    ehler
    0.15
    etik
    0.15
    Ø¡
    0.15
    elman
    0.14
    ’nun
    0.14
    Activations Density 0.166%

    No Known Activations