INDEX

Explanations

lines of code involving variable assignments and value manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ovo

-0.18

baugh

-0.16

.hs

-0.15

uli

-0.15

Ì£

-0.14

 unexpected

-0.14

ncy

-0.14

 Cour

-0.14

olph

-0.14

rey

-0.13

POSITIVE LOGITS

-pocket

0.18

èĤ©

0.15

conde

0.15

Pocket

0.15

erland

0.14

 Vita

0.14

-UA

0.14

xdc

0.14

à®¿à®

0.14

 Phillips

0.14

Activations Density 0.108%

lines of code involving variable assignments and value manipulations

No Comments

No Known Activations