INDEX

Explanations

phrases related to threats or dangers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

rint

-0.15

ehler

-0.15

amin

-0.15

 Worm

-0.15

iao

-0.15

arent

-0.15

agues

-0.14

.gstatic

-0.14

olest

-0.14

ledon

-0.14

POSITIVE LOGITS

 dangers

0.19

 danger

0.18

baar

0.16

çĬ¶

0.15

lug

0.15

elm

0.15

ources

0.15

ably

0.14

 Danger

0.14

Activations Density 0.029%

phrases related to threats or dangers

No Comments

No Known Activations