INDEX

Explanations

names and citations in academic references

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

isin

-0.15

deb

-0.14

ursal

-0.14

 JÃ¡

-0.14

 Interval

-0.14

 Conway

-0.14

nc

-0.14

 Michel

-0.14

xcb

-0.13

POSITIVE LOGITS

«

0.16

áº¯n

0.16

swick

0.14

Ø³ÙĪØ¨

0.14

 ÑģÐ¸Ð»Ñĥ

0.14

Ð½Ð°Ð´Ð»ÐµÐ¶

0.14

ÑıÐ´

0.13

quia

0.13

 Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»ÑĮ

0.13

ascus

0.13

Activations Density 0.007%

names and citations in academic references

No Comments

No Known Activations