INDEX

Explanations

phrases that express feelings, states of being, or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Certain

-0.18

Canceled

-0.17

imits

-0.15

Certain

-0.14

clude

-0.14

ibold

-0.14

arez

-0.14

awan

-0.13

elines

-0.13

egl

-0.13

POSITIVE LOGITS

 such

0.26

 incumbent

0.21

 neat

0.19

 SUCH

0.18

Such

0.18

 very

0.18

such

0.17

 important

0.17

 been

0.16

 Such

0.16

Activations Density 0.093%

phrases that express feelings, states of being, or conditions

No Comments

No Known Activations