INDEX

Explanations

terms related to specific industries and their products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lya

-0.15

fÃ¼hr

-0.15

å¸Ń

-0.14

åį

-0.14

.rd

-0.14

 åį

-0.14

isch

-0.14

 revert

-0.14

-0.13

lesai

-0.13

POSITIVE LOGITS

isphere

0.22

 realm

0.20

 industry

0.20

 world

0.20

 market

0.18

realm

0.18

 landscape

0.17

industry

0.17

 category

0.17

 sphere

0.16

Activations Density 0.134%

terms related to specific industries and their products or services

No Comments

No Known Activations

terms related to specific industries and their products or services

No Comments

No Known Activations