INDEX

Explanations

programming functions and expressions related to code generation and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

acier

-0.18

åĹ

-0.17

shal

-0.16

 Bourbon

-0.15

Dul

-0.14

Ð½Ð°ÑĤ

-0.14

(protocol

-0.14

YT

-0.14

",__

-0.14

lal

-0.14

POSITIVE LOGITS

mma

0.15

Ã¡r

0.14

ÑĥÐ¹

0.14

Gee

0.14

(#)

0.14

EOF

0.13

 alias

0.13

rad

0.13

amus

0.13

arda

0.13

Activations Density 0.105%

programming functions and expressions related to code generation and manipulation

No Comments

No Known Activations