INDEX

Explanations

instances of discussions or threads in an online forum or community

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Tob

-0.17

hor

-0.16

ãĥ¼ãĥķ

-0.16

 Hood

-0.14

Ã¶s

-0.14

ivy

-0.14

mile

-0.14

culus

-0.14

annon

-0.14

-profit

-0.14

POSITIVE LOGITS

atoria

0.15

gere

0.14

atorium

0.14

 Odds

0.14

 therap

0.14

ÛĮÙħ

0.14

heimer

0.13

cheid

0.13

Activations Density 0.002%

instances of discussions or threads in an online forum or community

No Comments

No Known Activations