INDEX

Explanations

references to significant events, figures, or concepts in a historical or academic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

antity

-0.16

ÐĲÑĢÑħÑĸÐ²

-0.15

.opend

-0.14

ãĥ³ãĥĦ

-0.14

 ÙħÙĨØ§Ø¨Ø¹

-0.13

 Addr

-0.13

 addCriterion

-0.13

ampion

-0.13

iks

-0.13

iaux

-0.13

POSITIVE LOGITS

kur

0.16

 Ð¿ÑĢÐ¾Ð²

0.15

 tripod

0.14

AYER

0.14

atr

0.14

ãĥ«ãĤ¯

0.13

oÅĪ

0.13

asto

0.13

 UIStoryboard

0.13

/part

0.13

Activations Density 0.431%

references to significant events, figures, or concepts in a historical or academic context

No Comments

No Known Activations