INDEX

Explanations

adjectives that describe size, depth, and intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

’s

-0.16

 slight

-0.15

bjerg

-0.15

 Dani

-0.14

abs

-0.14

/=

-0.14

quires

-0.13

 twin

-0.13

loor

-0.13

POSITIVE LOGITS

 à¹Ĩ

0.20

 enough

0.20

à¹Ĩ

0.20

/simple

0.19

(er

0.19

(est

0.18

arella

0.18

nest

0.17

ening

0.17

AGMA

0.17

Activations Density 0.257%

adjectives that describe size, depth, and intensity

No Comments

No Known Activations