INDEX

Explanations

punctuation marks and references to images or credits

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

anter

-0.17

ullan

-0.16

ouve

-0.16

oire

-0.16

rrha

-0.15

soever

-0.15

ãĥģãĥ¥

-0.15

Ú¯Ùĩ

-0.15

Ð¾Ð»Ð¶

-0.14

Ø§ØµÙĦ

-0.14

POSITIVE LOGITS

 Baths

0.15

iron

0.14

 McDon

0.14

ëįĶ

0.13

 Rank

0.13

.Lang

0.13

ãĤĽ

0.13

Equipment

0.13

 Equipment

0.13

lÄ±

0.13

Activations Density 0.079%

punctuation marks and references to images or credits

No Comments

No Known Activations