INDEX

Explanations

references to sections and formulas within a mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

lane

-0.15

Å¡ak

-0.15

 fors

-0.14

eling

-0.13

lico

-0.13

 Reynolds

-0.13

.baidu

-0.12

lying

-0.12

rema

-0.12

mada

-0.12

POSITIVE LOGITS

 materially

0.14

chio

0.14

gra

0.14

evi

0.13

atro

0.13

Ø§ÙĪÙĨØ¯

0.13

-fw

0.13

uard

0.13

Scoped

0.12

Ð»ÑİÑĩÐ°

0.12

Activations Density 0.057%

references to sections and formulas within a mathematical context

No Comments

No Known Activations