INDEX

Explanations

elements of mathematical notation and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ÅĽcie

-0.15

serter

-0.15

abin

-0.15

 Bale

-0.15

 Pony

-0.14

kus

-0.14

 Wong

-0.14

å¯Ħ

-0.14

ilen

-0.14

agan

-0.13

POSITIVE LOGITS

0.19

0.16

oder

0.15

lescope

0.14

.inflate

0.14

piel

0.14

 Heidi

0.14

ãģ£ãģ¦ãĤĤ

0.14

¹Ħ

0.13

veau

0.13

Activations Density 0.302%

elements of mathematical notation and formatting

No Comments

No Known Activations