© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 30793
    Prev
    Next
    INDEX
    Explanations

    instances of effort, research, and planning 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 @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollider
    -0.16
    geç
    -0.15
    taÅŁ
    -0.13
    ichert
    -0.13
    enant
    -0.13
    èĥ½åĬĽ
    -0.13
    .Binding
    -0.12
    andler
    -0.12
    ensburg
    -0.12
     Ending
    -0.12
    POSITIVE LOGITS
     research
    0.33
     investigation
    0.28
     deliber
    0.27
     contempl
    0.27
     strateg
    0.27
     thought
    0.26
     analysis
    0.26
     thinking
    0.26
     detective
    0.25
     experimentation
    0.25
    Activations Density 0.342%

    No Known Activations