INDEX

Explanations

content related to healthcare news and policy discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

orrent

-0.18

upert

-0.15

 æĻ®

-0.14

Ø§Ø©

-0.14

axon

-0.14

ÑĪÑĮ

-0.14

Unified

-0.13

Ã¨o

-0.13

 Hayden

-0.13

NAT

-0.13

POSITIVE LOGITS

onda

0.17

à¸§à¸Ķ

0.16

0.14

ospace

0.14

(æľ¨

0.14

subcategory

0.13

roz

0.13

LOPT

0.13

uga

0.13

ç¤¾

0.13

Activations Density 0.139%

content related to healthcare news and policy discussions

No Comments

No Known Activations