INDEX

Explanations

expressions related to preference or partiality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ed

-0.17

eso

-0.17

endor

-0.16

enen

-0.15

elter

-0.15

expo

-0.15

els

-0.15

elix

-0.15

en

-0.14

emb

-0.14

POSITIVE LOGITS

ably

0.36

ing

0.23

ited

0.23

ABILITY

0.23

able

0.21

ABLE

0.21

 favor

0.20

ites

0.20

 Favor

0.20

ize

0.20

Activations Density 0.023%

expressions related to preference or partiality

No Comments

No Known Activations