INDEX

Explanations

technical terms related to programming and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

lero

-0.15

uggy

-0.15

çĽ´

-0.15

antage

-0.14

ulture

-0.14

antages

-0.14

rogram

-0.14

PEAR

-0.14

ended

-0.14

inel

-0.14

POSITIVE LOGITS

 serialVersionUID

0.20

.parseLong

0.16

qing

0.15

arith

0.15

zb

0.15

chu

0.15

anske

0.14

jan

0.14

usaha

0.14

Activations Density 0.013%

technical terms related to programming and data manipulation

No Comments

No Known Activations