INDEX

Explanations

scientific notation and variables commonly used in mathematical or scientific contexts

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

 cáº£nh

-0.15

Ľi

-0.15

æķ

-0.15

åĳ¨æľŁ

-0.15

ÐµÑĢÑĸÐ³

-0.15

uman

-0.15

 Princess

-0.15

Ler

-0.14

ishops

-0.14

weep

-0.14

POSITIVE LOGITS

 showers

0.19

ISR

0.18

 Shower

0.17

 fragmentation

0.17

 shower

0.16

 coal

0.16

 cross

0.15

ISR

0.15

 Smoking

0.15

cuts

0.15

Activations Density 0.003%

scientific notation and variables commonly used in mathematical or scientific contexts

No Comments

No Known Activations