INDEX

Explanations

references to governmental and institutional entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ngb

-0.15

âĢ¦↵↵↵

-0.15

vetica

-0.15

ë²Į

-0.14

Vtbl

-0.14

ëĨ

-0.13

 Vulner

-0.13

nÃ¡m

-0.13

``

-0.13

kili

-0.13

POSITIVE LOGITS

efe

0.14

Ã¼rn

0.13

 rout

0.13

psi

0.13

/p

0.13

ees

0.12

ures

0.12

ers

0.12

Â®

0.12

adians

0.12

Activations Density 0.288%

references to governmental and institutional entities

No Comments

No Known Activations