INDEX

Explanations

key descriptors and elements related to product details and collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ãĥ¼ãĤ¯

-0.15

th

-0.15

 struggle

-0.15

anger

-0.14

toi

-0.14

ondo

-0.14

_bias

-0.13

ka

-0.13

uml

-0.13

brid

-0.13

POSITIVE LOGITS

optera

0.17

/GPL

0.16

orer

0.15

slaught

0.15

.ud

0.15

ë¦¬ìĸ´

0.14

ocking

0.14

uali

0.14

ÎŃÏģÎ±

0.14

ascript

0.14

Activations Density 0.266%

key descriptors and elements related to product details and collaborations

No Comments

No Known Activations