INDEX

Explanations

words that describe attributes of layered or ornate structures and materials

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

Ø§Ø¨ÛĮ

-0.16

-inst

-0.15

 Nack

-0.15

aÅ¾

-0.14

 ******************************************************************************↵

-0.14

emoc

-0.13

PWD

-0.13

istrovstvÃŃ

-0.13

omaly

-0.13

ÑģÑĤÑĭ

-0.13

POSITIVE LOGITS

allon

0.17

ateur

0.16

otted

0.15

gers

0.14

Ð°ÑĤÐ¾ÑĢ

0.14

 threshold

0.14

 Lever

0.14

ifton

0.13

Reviewer

0.13

amiliar

0.13

Activations Density 0.221%

words that describe attributes of layered or ornate structures and materials

No Comments

No Known Activations