INDEX

Explanations

mathematical expressions and symbols related to equations and theoretical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

cur

-0.15

ulin

-0.15

 Sous

-0.14

 Townsend

-0.14

iko

-0.14

 Abraham

-0.14

kowski

-0.13

Ã¡ct

-0.13

-Token

-0.13

 Chun

-0.13

POSITIVE LOGITS

TRANS

0.25

 transpose

0.25

-trans

0.24

transpose

0.24

 Trans

0.23

Trans

0.21

 trans

0.21

Transpose

0.21

trans

0.20

tran

0.20

Activations Density 0.022%

mathematical expressions and symbols related to equations and theoretical concepts

No Comments

No Known Activations