INDEX

Explanations

references to notable literary figures and their works

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

 which

-0.18

-0.17

owards

-0.17

etc

-0.15

 meaning

-0.15

 welche

-0.15

 endeavour

-0.15

 otherwise

-0.15

huh

-0.15

POSITIVE LOGITS

ousel

0.16

 å¾ĴæŃ©

0.15

 nons

0.15

 amid

0.15

.undefined

0.14

ÃŃl

0.14

;if

0.14

udur

0.14

:return

0.14

olet

0.14

Activations Density 1.237%

references to notable literary figures and their works

No Comments

No Known Activations