INDEX

Explanations

references to museums and museum-related terminology

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

åĵ

-0.16

 uniformly

-0.15

 rast

-0.15

ç

-0.14

Ã»t

-0.14

odel

-0.14

itas

-0.14

pev

-0.14

 organic

-0.14

emer

-0.14

POSITIVE LOGITS

ioctl

0.18

artz

0.15

ogg

0.15

iest

0.15

ì²ł

0.14

ActionResult

0.14

Äĩe

0.14

iversite

0.14

Å¡ti

0.14

gebra

0.14

Activations Density 0.059%

references to museums and museum-related terminology

No Comments

No Known Activations