INDEX

Explanations

terms related to artificial intelligence and technology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ogh

-0.16

anto

-0.16

achel

-0.15

samp

-0.15

 audiences

-0.14

bral

-0.14

 kanal

-0.14

Ø²Ø¯

-0.14

éĽª

-0.13

 Anthony

-0.13

POSITIVE LOGITS

.dtd

0.15

 Hubb

0.15

SEC

0.15

ubb

0.15

uby

0.14

éĨ´

0.14

ãĥ³ãĤ¯

0.14

ocup

0.14

ÑĢÐ°Ð²Ð°

0.14

intree

0.14

Activations Density 0.015%

terms related to artificial intelligence and technology

No Comments

No Known Activations