INDEX

Explanations

concepts related to health, well-being, and medical procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.sdk

-0.15

aravel

-0.15

gross

-0.14

ÃŃl

-0.14

ÑĢÐ°Ð¶

-0.14

 Kostenlos

-0.14

 Ø¨ØŃ

-0.14

 Gross

-0.14

ilden

-0.14

isan

-0.13

POSITIVE LOGITS

oro

0.17

anko

0.17

 sling

0.16

wart

0.16

hou

0.15

ther

0.15

èĬ³

0.15

liqu

0.15

rowable

0.14

Nug

0.14

Activations Density 0.049%

concepts related to health, well-being, and medical procedures

No Comments

No Known Activations