INDEX

Explanations

keywords and terms related to technical or scientific concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.16

èĨ

-0.15

 Ø®ÙĦ

-0.15

omes

-0.14

 moon

-0.14

 Hood

-0.14

éĺ´

-0.14

oment

-0.13

bomb

-0.13

 Moon

-0.13

POSITIVE LOGITS

ekli

0.15

allis

0.15

egie

0.15

.Interop

0.14

elik

0.14

à¸Ĺà¸²à¸Ļ

0.14

latlong

0.14

eka

0.14

AMED

0.14

 soudu

0.14

Activations Density 0.003%

keywords and terms related to technical or scientific concepts

No Comments

No Known Activations