INDEX

Explanations

technical jargon and specific terminology related to scientific and medical contexts

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

zin

-0.18

lit

-0.16

SPATH

-0.15

_equiv

-0.15

chia

-0.15

HITE

-0.14

ova

-0.14

Regs

-0.14

ependency

-0.14

à¤łà¤¨

-0.14

POSITIVE LOGITS

0.26

 (“

0.20

 abbreviated

0.16

("

0.16

.safe

0.16

(A

0.15

 known

0.15

(PC

0.15

Ð»Ñİ

0.15

ennen

0.15

Activations Density 0.134%

technical jargon and specific terminology related to scientific and medical contexts

No Comments

No Known Activations