INDEX

Explanations

phrases indicating causes of death or health-related issues

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

neas

-0.15

acle

-0.14

abel

-0.14

ooke

-0.14

okt

-0.14

ipar

-0.14

aling

-0.14

 resolutions

-0.14

enso

-0.14

DK

-0.14

POSITIVE LOGITS

 Competitive

0.16

 competitive

0.16

 contract

0.15

ustos

0.15

IFS

0.14

 secular

0.14

Utf

0.14

elles

0.14

competitive

0.14

ofi

0.14

Activations Density 0.017%

phrases indicating causes of death or health-related issues

No Comments

No Known Activations