INDEX

Explanations

references to tumors and cancer

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ê¶ģ

-0.17

quine

-0.15

loo

-0.14

 borough

-0.14

 normals

-0.14

.namespace

-0.13

 prostituer

-0.13

å¿

-0.13

Ð¡Ð¡Ðł

-0.13

Fee

-0.13

POSITIVE LOGITS

oft

0.15

ickers

0.14

inker

0.14

 desar

0.13

ylie

0.13

vip

0.13

 Bookmark

0.13

 Ãĺ

0.13

Activations Density 0.011%

references to tumors and cancer

No Comments

No Known Activations