INDEX

Explanations

syntax related to file paths and programming code errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

]={↵

-0.16

holm

-0.15

fony

-0.15

 Infect

-0.15

doll

-0.14

ÄįnÃŃk

-0.14

'gc

-0.14

 Caldwell

-0.14

PIO

-0.13

èº

-0.13

POSITIVE LOGITS

0.40

âĢª

0.27

0.26

0.24

 drive

0.23

0.22

 Program

0.21

('\\

0.21

 path

0.20

Activations Density 0.070%

syntax related to file paths and programming code errors

No Comments

No Known Activations