INDEX

Explanations

names of significant people, awards, and technologies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

bard

-0.15

Ð½ÑĮ

-0.15

 irre

-0.15

seau

-0.13

ults

-0.13

otty

-0.13

 Anth

-0.13

 Evet

-0.13

xD

-0.13

tec

-0.13

POSITIVE LOGITS

otate

0.15

scribe

0.15

egrator

0.15

rale

0.14

:async

0.14

.COMP

0.14

atis

0.14

ä¸ģ

0.14

Wor

0.14

ATUS

0.14

Activations Density 0.009%

names of significant people, awards, and technologies

No Comments

No Known Activations