INDEX

Explanations

terms related to computer systems and file management

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

strup

-0.19

áº¬

-0.17

-0.15

emie

-0.15

 Norris

-0.14

asso

-0.14

aney

-0.14

warf

-0.14

 Himself

-0.13

hof

-0.13

POSITIVE LOGITS

0.17

 veter

0.16

ÐµÐ´Ð°Ðº

0.15

wide

0.15

zcze

0.14

idir

0.14

isko

0.14

ahoo

0.14

Activations Density 0.022%

terms related to computer systems and file management

No Comments

No Known Activations