INDEX

Explanations

instances of comparative or contrasting phrases

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

/stdc

-0.19

avit

-0.16

rts

-0.14

utral

-0.14

.fil

-0.14

QUIRE

-0.14

-0.13

ãģ£ãģ¦ãĤĤ

-0.13

lek

-0.13

.ascii

-0.13

POSITIVE LOGITS

enco

0.15

Ģìŀ¥

0.14

woord

0.14

OrElse

0.14

kinson

0.13

EP

0.13

 indiv

0.13

 Russo

0.13

 Cart

0.13

ãĥŃãĥ³

0.13

Activations Density 0.109%

instances of comparative or contrasting phrases

No Comments

No Known Activations