INDEX

Explanations

numerical information related to academic or professional timelines and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ago

-0.14

ãĥĢãĥ¼

-0.14

 ==============================================================

-0.14

bac

-0.14

uc

-0.14

 ilma

-0.13

ulmasÄ±

-0.13

pom

-0.13

asc

-0.13

ÑĥÑĪÐºÐ°

-0.13

POSITIVE LOGITS

azzi

0.18

 Present

0.18

 present

0.16

Ã¶rt

0.16

vester

0.15

ught

0.14

tyard

0.14

Ð¾Ð´Ð¾

0.14

Ð¾ÐºÐ¸

0.13

Present

0.13

Activations Density 0.014%

numerical information related to academic or professional timelines and positions

No Comments

No Known Activations