INDEX

Explanations

academic affiliations and institutional terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ymoon

-0.14

-0.13

Ãŀ

-0.13

ì¸

-0.13

.sponge

-0.13

tbody

-0.13

macros

-0.13

pesan

-0.13

olis

-0.13

ateria

-0.13

POSITIVE LOGITS

-caret

0.16

efa

0.15

ãĤ¹ãĤ³

0.15

ìĭł

0.15

steder

0.15

sans

0.14

ibri

0.14

ekim

0.14

otto

0.14

abin

0.13

Activations Density 0.015%

academic affiliations and institutional terminology

No Comments

No Known Activations