© 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. 31-LLAMASCOPE-RES-32K
    11. 16632
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to stock performance and financial metrics

    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
     Methods
    -0.20
     Concepts
    -0.20
     Principles
    -0.19
    parameters
    -0.18
     Functions
    -0.17
    Methods
    -0.17
     Features
    -0.17
    Parameters
    -0.17
     Conditions
    -0.16
     Factors
    -0.16
    POSITIVE LOGITS
     element
    0.41
     feature
    0.40
     option
    0.38
     factor
    0.37
     thing
    0.37
     ingredient
    0.37
     argument
    0.37
     attribute
    0.36
     aspect
    0.36
     idea
    0.35
    Activations Density 0.358%

    No Known Activations