INDEX

Explanations

specific details related to technical programs and speaker information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.14

 diff

-0.14

cri

-0.14

omal

-0.14

tem

-0.14

.getOwnProperty

-0.13

sten

-0.13

POSITIVE LOGITS

ãģĹãģªãģĦ

0.16

ÑĩÐµ

0.16

macros

0.16

PRETTY

0.15

Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.15

-gradient

0.15

PÅĻÃŃ

0.15

:variables

0.15

-addons

0.14

ÑĢÐ°Ð²Ð¸

0.14

Activations Density 0.238%

specific details related to technical programs and speaker information

No Comments

No Known Activations