INDEX

Explanations

phrases that describe appearances or visual characteristics

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

roker

-0.15

utra

-0.14

ADX

-0.14

 Ú¯ÛĮØ±ÛĮ

-0.14

iet

-0.14

Ð¸ÑģÑĤÑĢÐ°

-0.14

looking

-0.14

æ´¥

-0.14

oeff

-0.13

POSITIVE LOGITS

 like

0.43

 Like

0.36

like

0.35

Like

0.34

 LIKE

0.31

LIKE

0.30

-like

0.28

_like

0.27

 likes

0.25

.like

0.24

Activations Density 0.007%

phrases that describe appearances or visual characteristics

No Comments

No Known Activations