© 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. 25-LLAMASCOPE-RES-32K
    11. 11545
    Prev
    Next
    INDEX
    Explanations

    references to time and its management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     periodic
    -0.15
    ãĥ³ãĤ¬
    -0.15
    ãĥ³ãĥij
    -0.15
    thur
    -0.15
    efe
    -0.14
    ereco
    -0.14
    Ñıг
    -0.14
    .opts
    -0.14
    asher
    -0.14
    οÏħλ
    -0.14
    POSITIVE LOGITS
     spend
    0.96
     spent
    0.94
     spending
    0.88
     Spend
    0.86
     spends
    0.86
    spent
    0.84
     Spending
    0.77
     spender
    0.61
     expenditure
    0.52
     devoted
    0.46
    Activations Density 0.293%

    No Known Activations