INDEX

Explanations

phrases that indicate conditions, requirements, or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

apel

-0.19

ÄħÅ¼

-0.16

ëįĶëĭĪ

-0.15

.mipmap

-0.15

zn

-0.14

Ð¾ÑĢÐ¾Ð½Ð¸

-0.14

_DECREF

-0.14

lik

-0.14

pone

-0.14

.partition

-0.14

POSITIVE LOGITS

iyet

0.19

oyer

0.17

ucu

0.16

xo

0.14

 Kore

0.14

uts

0.14

 à¹Ĩ

0.14

iyeti

0.13

 Taylor

0.13

cri

0.13

Activations Density 0.035%

phrases that indicate conditions, requirements, or limitations

No Comments

No Known Activations