INDEX

Explanations

schema-related tags or formats in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

NamedQuery

-0.16

iven

-0.16

ori

-0.16

ong

-0.15

iten

-0.15

clus

-0.15

ao

-0.15

uppy

-0.15

igen

-0.15

chl

-0.15

POSITIVE LOGITS

owitz

0.14

 strap

0.14

rows

0.14

 Cham

0.13

å¯¸

0.13

 nonatomic

0.13

 Sweep

0.13

ãĤ¦ãĥĪ

0.13

 Pure

0.13

.cms

0.13

Activations Density 0.000%

schema-related tags or formats in the text

No Comments

No Known Activations