INDEX

Explanations

specific numeric and coded data points or terms related to statistics and conditions in various contexts

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Questions

-0.15

Questions

-0.14

 Symbols

-0.14

/questions

-0.14

unnable

-0.14

questions

-0.13

 Queries

-0.13

infeld

-0.13

 EVEN

-0.13

 questions

-0.13

POSITIVE LOGITS

 reviewing

0.15

 blogging

0.15

 trag

0.14

Sadly

0.14

sad

0.14

ÙħØ§ÙĦ

0.14

anes

0.14

 fortunate

0.14

 unfortunately

0.14

 involved

0.14

Activations Density 0.027%

specific numeric and coded data points or terms related to statistics and conditions in various contexts

No Comments

No Known Activations