INDEX

Explanations

phrases emphasizing significant actions or steps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

odesk

-0.16

Ð°ÐºÑģÐ¸Ð¼

-0.14

ripper

-0.14

.mybatisplus

-0.14

.opendaylight

-0.14

ãĤ¤ãĥĦ

-0.13

edback

-0.13

arga

-0.13

weeney

-0.13

JECTED

-0.13

POSITIVE LOGITS

 step

0.67

step

0.58

 Step

0.57

 first

0.54

Step

0.52

 steps

0.49

-step

0.49

_step

0.47

first

0.46

STEP

0.46

Activations Density 0.124%

phrases emphasizing significant actions or steps

No Comments

No Known Activations