INDEX

Explanations

references to corrections and the act of correcting errors or mistakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iece

-0.16

loub

-0.15

lit

-0.15

olt

-0.15

dash

-0.14

kest

-0.14

isl

-0.14

uet

-0.14

/desktop

-0.13

ÐµÑĢÐ¸Ð½

-0.13

POSITIVE LOGITS

zeitig

0.15

hue

0.15

0.14

 Exercises

0.14

/update

0.14

Ø´ÙĪ

0.14

vascular

0.14

ãĤ¤ãĥĪ

0.14

åĩĨ

0.14

_runtime

0.14

Activations Density 0.016%

references to corrections and the act of correcting errors or mistakes

No Comments

No Known Activations