INDEX

Explanations

technical jargon and specific data types related to programming events and messages

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

-0.86

-0.80

-0.78

-0.65

-0.62

-0.60

-0.57

.↵

-0.51

-0.50

in

-0.50

POSITIVE LOGITS

_QMARK

0.30

IIIK

0.29

ëį°ìĿ´íĬ¸

0.26

íĨłíĨł

0.26

ï»¿#

0.25

âĸį

0.25

KANJI

0.25

âĢ¦”↵↵

0.24

âĢ¦"↵↵

0.24

_NONNULL

0.24

Activations Density 0.017%

technical jargon and specific data types related to programming events and messages

No Comments

No Known Activations