© 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. 18-LLAMASCOPE-RES-32K
    11. 29177
    Prev
    Next
    INDEX
    Explanations

    temporal expressions related to time frames and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGTON
    -0.16
     Roz
    -0.15
    _DET
    -0.15
    ington
    -0.14
     Dot
    -0.14
    ospace
    -0.14
    lvl
    -0.14
    -hours
    -0.13
     briefly
    -0.13
    nop
    -0.13
    POSITIVE LOGITS
    alendar
    0.20
     ká»ĥ
    0.19
     counted
    0.19
    /gtest
    0.17
     counting
    0.17
    ãģĭãģij
    0.15
     poÄį
    0.15
     countdown
    0.15
    abis
    0.15
     putas
    0.15
    Activations Density 0.065%

    No Known Activations