INDEX

Explanations

references to strategies and structured experiences related to digital or online contexts

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

yk

-0.17

cname

-0.16

ania

-0.16

atype

-0.15

inu

-0.15

Materials

-0.14

osu

-0.14

rier

-0.14

ilon

-0.14

é»İ

-0.14

POSITIVE LOGITS

ÙħØ¯

0.15

nett

0.15

.tap

0.14

 ÑģÐ²Ð¾Ð¸

0.14

(æĹ¥

0.13

ÅĽcie

0.13

 their

0.13

 Ø§ÙĤØªØµ

0.13

airs

0.13

Activations Density 0.020%

references to strategies and structured experiences related to digital or online contexts

No Comments

No Known Activations