INDEX

Explanations

words related to scientific or academic terms, particularly those ending with the suffix 'al'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

esh

-0.20

es

-0.20

ed

-0.20

eler

-0.19

ester

-0.19

el

-0.18

em

-0.17

edb

-0.16

elial

-0.16

ex

-0.16

POSITIVE LOGITS

dehyde

0.21

te

0.19

ty

0.19

culated

0.19

ists

0.18

ised

0.17

ted

0.17

ized

0.17

mente

0.17

ts

0.17

Activations Density 0.208%

words related to scientific or academic terms, particularly those ending with the suffix 'al'

No Comments

No Known Activations