INDEX

Explanations

references to location and geographic areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

sink

-0.19

ystate

-0.18

KeySpec

-0.17

ÐĶÐļ

-0.16

-ng

-0.15

Ð¾Ð³ÐµÐ½

-0.15

lix

-0.15

resi

-0.15

 Stam

-0.15

ÃŃÅ¡

-0.15

POSITIVE LOGITS

car

0.21

bor

0.18

Car

0.16

 Atlantic

0.16

utton

0.15

ogy

0.15

 trans

0.15

 Gould

0.15

Car

0.14

th

0.14

Activations Density 0.029%

references to location and geographic areas

No Comments

No Known Activations