INDEX

Explanations

rules and conditions related to usage restrictions and compatibility in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

islav

-0.15

-0.14

.isHidden

-0.14

-0.13

inya

-0.13

otos

-0.13

pend

-0.13

bedo

-0.13

.fromLTRB

-0.13

POSITIVE LOGITS

 mess

0.35

 ruin

0.31

 interfere

0.30

 damage

0.30

 harm

0.30

mess

0.29

 Mess

0.29

 disrupt

0.28

Mess

0.28

 disturb

0.27

Activations Density 0.916%

rules and conditions related to usage restrictions and compatibility in different contexts

No Comments

No Known Activations