INDEX

Explanations

guidance and recommendations for various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zbek

-0.16

amina

-0.14

vez

-0.14

rena

-0.14

vely

-0.14

omin

-0.14

Ð»Ð¾Ñĩ

-0.14

Bou

-0.14

ext

-0.14

factory

-0.14

POSITIVE LOGITS

 Seas

0.18

.GetCurrent

0.15

isay

0.15

cope

0.14

-Out

0.14

 Gong

0.14

aris

0.14

ÎºÎµ

0.14

agrant

0.13

Activations Density 0.087%

guidance and recommendations for various situations

No Comments

No Known Activations