INDEX

Explanations

references to interviews and social media engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Brah

-0.15

stÃŃ

-0.14

kazy

-0.14

onal

-0.14

isin

-0.14

 Plato

-0.14

zyst

-0.14

say

-0.13

eron

-0.13

POSITIVE LOGITS

0.16

nova

0.15

sono

0.14

'id

0.13

à¤Ĥà¤§à¤¨

0.13

 Ð·Ð³

0.13

hle

0.13

sense

0.12

èĬ¸

0.12

icular

0.12

Activations Density 0.022%

references to interviews and social media engagement

No Comments

No Known Activations