INDEX

Explanations

specific numerical values or symbols related to measurements

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

-0.20

tom

-0.18

 latter

-0.18

in

-0.18

-0.16

Ð¼Ð¾Ð¼

-0.16

-0.15

nave

-0.15

-0.14

POSITIVE LOGITS

VERR

0.17

ãĥ¼ãĥĵ

0.16

(...)↵

0.15

0.14

:↵

0.14

amble

0.14

riter

0.13

greSQL

0.13

.TabStop

0.13

Activations Density 0.024%

specific numerical values or symbols related to measurements

No Comments

No Known Activations