INDEX

Explanations

mentions of locations, specifically cities or educational institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÑħÐ¾Ð²

-0.16

pNet

-0.15

coma

-0.14

.mvp

-0.14

tae

-0.13

è¾

-0.13

.multipart

-0.13

andler

-0.13

itchen

-0.13

Ø§ÙĦÙĥ

-0.13

POSITIVE LOGITS

 Rouge

0.27

 rouge

0.19

leurs

0.18

 clin

0.16

 Rogue

0.15

 Bolt

0.15

rou

0.15

leur

0.15

clin

0.15

ummer

0.15

Activations Density 0.007%

mentions of locations, specifically cities or educational institutions

No Comments

No Known Activations