INDEX

Explanations

references to roles and positions within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

antan

-0.18

atÃ³

-0.16

Ã´i

-0.16

ekim

-0.16

elsen

-0.16

MAND

-0.14

okt

-0.14

ÙħÙĪØ¯

-0.14

ebi

-0.14

rray

-0.13

POSITIVE LOGITS

raries

0.17

ager

0.17

/ns

0.15

imar

0.14

erman

0.14

ira

0.14

 Mark

0.14

 brid

0.13

ke

0.13

Activations Density 0.120%

references to roles and positions within organizations

No Comments

No Known Activations