INDEX

Explanations

programming functions or methods being defined or called

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

wick

-0.17

kek

-0.16

artz

-0.15

Ð¾ÑĤÐ°

-0.15

heck

-0.14

otta

-0.14

igit

-0.14

tick

-0.14

onta

-0.13

xad

-0.13

POSITIVE LOGITS

âĨĴâĨĴ

0.15

ocard

0.14

 Duchess

0.14

ivol

0.14

OTP

0.13

evin

0.13

 ØµÙĦÙī

0.13

URT

0.13

oney

0.13

Activations Density 0.020%

programming functions or methods being defined or called

No Comments

No Known Activations