INDEX

Explanations

references to extraordinary qualities or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Henderson

-0.15

Ã¨n

-0.15

ersen

-0.15

endi

-0.14

-Ð¿

-0.14

omer

-0.14

odes

-0.14

åħ¥ãĤĬ

-0.14

old

-0.14

ipp

-0.14

POSITIVE LOGITS

icut

0.17

IPA

0.16

Ù

0.16

 mortal

0.14

xaf

0.14

lest

0.14

preter

0.14

Å¾i

0.14

memberOf

0.14

ichten

0.13

Activations Density 0.027%

references to extraordinary qualities or experiences

No Comments

No Known Activations