INDEX

Explanations

references to specific locations and notable individuals

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

 bÃŃ

-0.16

ulos

-0.15

elerik

-0.15

 wealthy

-0.14

idor

-0.14

 retired

-0.14

dummy

-0.14

 Laure

-0.14

 Donald

-0.14

POSITIVE LOGITS

roach

0.16

ake

0.15

antiago

0.14

uchen

0.14

ÃĹ↵↵

0.14

 ÑģÑĤÐ¾Ñı

0.14

 Werk

0.14

anes

0.14

ugen

0.14

.TXT

0.13

Activations Density 0.230%

references to specific locations and notable individuals

No Comments

No Known Activations