INDEX

Explanations

numerical locations or addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑĤÐ¾Ð½

-0.14

 Evel

-0.13

.nlm

-0.13

ooo

-0.13

emme

-0.13

 Fraser

-0.13

osas

-0.13

æ¬ł

-0.13

wp

-0.12

anton

-0.12

POSITIVE LOGITS

 United

0.20

United

0.18

apid

0.15

 UNITED

0.15

 Uncategorized

0.15

plits

0.15

lav

0.14

ibi

0.14

Ð»ÑĥÑĪ

0.14

ìĤ°

0.14

Activations Density 0.097%

numerical locations or addresses

No Comments

No Known Activations

numerical locations or addresses

No Comments

No Known Activations