INDEX

Explanations

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

rzy

-0.17

zig

-0.16

ensem

-0.16

formats

-0.15

rych

-0.15

lea

-0.14

panse

-0.14

ï»¿#

-0.14

.idea

-0.14

raison

-0.14

POSITIVE LOGITS

 standpoint

0.34

 perspective

0.32

 outset

0.25

 perspectives

0.23

 beginning

0.22

 Perspective

0.21

/to

0.21

oth

0.21

pers

0.19

 depths

0.19

Activations Density 0.079%

occurrences of the word "the."

No Comments

No Known Activations