INDEX

Explanations

sections related to geographical locations or regional entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ibold

-0.19

nelly

-0.17

XS

-0.16

abase

-0.15

sWith

-0.15

uong

-0.14

Ã©o

-0.14

alette

-0.14

ensor

-0.14

iento

-0.14

POSITIVE LOGITS

 Spor

0.15

usting

0.15

agli

0.15

éĻ

0.14

!/

0.14

isia

0.13

 hall

0.13

_delegate

0.13

)↵↵↵↵↵↵↵↵

0.13

 Pied

0.13

Activations Density 0.002%

sections related to geographical locations or regional entities

No Comments

No Known Activations