INDEX

Explanations

prominent names or titles associated with significant roles or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 bÃł

-0.14

adle

-0.14

LEASE

-0.13

 SUBSTITUTE

-0.13

 Reserve

-0.13

azÄ±

-0.13

 modern

-0.13

ama

-0.13

rus

-0.12

 Bach

-0.12

POSITIVE LOGITS

 Davies

0.14

ForMember

0.14

ëħĦëıĦ

0.14

è¿Ļç§į

0.13

 anlamda

0.13

 Griff

0.13

ByExample

0.13

Aspect

0.13

à¸ļ

0.13

.BackgroundImage

0.13

Activations Density 0.552%

prominent names or titles associated with significant roles or events

No Comments

No Known Activations