INDEX

Explanations

references to individuals and groups in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.17

³

-0.16

NECT

-0.16

ÑĩÐ¸Ð¹

-0.15

omik

-0.15

.scalablytyped

-0.14

ARAM

-0.14

ozem

-0.14

uur

-0.14

POSITIVE LOGITS

.has

0.39

Has

0.37

-has

0.36

has

0.35

_has

0.34

 hath

0.34

Has

0.34

 Have

0.33

æľī

0.33

-have

0.32

Activations Density 0.185%

references to individuals and groups in various contexts

No Comments

No Known Activations

references to individuals and groups in various contexts

No Comments

No Known Activations