INDEX

Explanations

instances of mathematical notation, particularly involving parentheses, braces, and limits

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

á»į

-0.16

hausen

-0.16

lessly

-0.16

aye

-0.15

 Erotik

-0.14

"urls

-0.14

$LANG

-0.14

hiba

-0.14

íĮĢ

-0.14

verts

-0.14

POSITIVE LOGITS

arrow

0.21

Arrow

0.18

Į¨

0.18

 Arrow

0.16

®

0.15

_ABS

0.15

ExecutionContext

0.15

lasses

0.15

 arrow

0.14

Activations Density 0.029%

instances of mathematical notation, particularly involving parentheses, braces, and limits

No Comments

No Known Activations