INDEX

Explanations

phrases related to professional or organizational responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rane

-0.15

und

-0.15

uu

-0.15

Ã¡zd

-0.14

oggler

-0.14

 zwar

-0.14

acades

-0.13

ÏĦÎ®

-0.13

essel

-0.13

but

-0.13

POSITIVE LOGITS

 also

0.19

also

0.17

 takÅ¼e

0.17

 Ø£ÙĬØ¶Ø§

0.17

 actual

0.16

 equally

0.16

actual

0.16

 ones

0.15

 tambiÃ©n

0.15

Also

0.15

Activations Density 0.233%

phrases related to professional or organizational responsibility

No Comments

No Known Activations