© 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. 14-LLAMASCOPE-RES-32K
    11. 14267
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the concept of consequences in various contexts

    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
    UDGE
    -0.14
    aser
    -0.14
    aurus
    -0.14
    خاÙĨÙĩ
    -0.14
    udge
    -0.13
    oria
    -0.13
    ded
    -0.13
    orris
    -0.13
    ti
    -0.13
    /board
    -0.13
    POSITIVE LOGITS
    물ìĿĦ
    0.19
     consequences
    0.18
    anch
    0.17
    urs
    0.17
    imas
    0.17
    antly
    0.15
    물
    0.15
    edis
    0.15
    /effects
    0.15
    yro
    0.14
    Activations Density 0.034%

    No Known Activations