INDEX

Explanations

questions beginning with "Did you" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ochen

-0.18

ohn

-0.17

HR

-0.15

_DEFINE

-0.15

 Champion

-0.13

stroy

-0.13

Ð¾Ð½ÑĮ

-0.13

oons

-0.13

åĳĬ

-0.13

shall

-0.13

POSITIVE LOGITS

 ever

0.32

 notice

0.20

ever

0.20

 jamais

0.19

 notices

0.19

 noticed

0.19

 EVER

0.19

 Ever

0.18

 Notice

0.18

-ever

0.17

Activations Density 0.025%

questions beginning with "Did you" or variations thereof

No Comments

No Known Activations