INDEX

Explanations

expressions related to personal views and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

endl

-0.16

ilder

-0.16

Ð¾ÑıÐ½

-0.16

elp

-0.15

Ð²Ð¸

-0.15

erk

-0.15

foot

-0.14

 Gallagher

-0.14

esk

-0.14

POSITIVE LOGITS

aires

0.18

naires

0.18

sher

0.15

 Maker

0.14

naire

0.14

IRMWARE

0.14

embr

0.14

AsyncResult

0.14

 OTHERWISE

0.14

Activations Density 0.025%

expressions related to personal views and opinions

No Comments

No Known Activations