INDEX

Explanations

specific technical or medical terms related to definitions or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ION

-0.17

æ¿

-0.16

onen

-0.16

elta

-0.15

stral

-0.15

oder

-0.15

 fabs

-0.15

aml

-0.15

POOL

-0.15

iones

-0.14

POSITIVE LOGITS

aba

0.16

adow

0.16

áº¡c

0.15

'gc

0.14

pearance

0.14

 Clarence

0.14

PageRoute

0.14

Prot

0.14

ApiResponse

0.14

ress

0.14

Activations Density 0.216%

specific technical or medical terms related to definitions or classifications

No Comments

No Known Activations