INDEX

Explanations

terms related to regulations and compliance issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

VML

-0.17

damage

-0.15

 Damage

-0.15

 damage

-0.15

Damage

-0.15

kus

-0.15

ÃŃk

-0.14

 Goose

-0.14

EDA

-0.14

'gc

-0.14

POSITIVE LOGITS

 corrective

0.25

 flagged

0.24

 flags

0.22

-flag

0.21

 flag

0.21

Correction

0.21

 Correct

0.20

flag

0.20

 correcting

0.20

 corrections

0.20

Activations Density 0.058%

terms related to regulations and compliance issues

No Comments

No Known Activations