INDEX

Explanations

technical terms and phrases related to programming functions and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

oston

-0.18

 Goodman

-0.16

 Resp

-0.15

Ð¾Ð±ÑĢÐ°Ð

-0.15

nte

-0.14

 resp

-0.14

edo

-0.14

-floor

-0.14

resp

-0.14

avel

-0.14

POSITIVE LOGITS

 arguments

0.41

 argument

0.36

 args

0.33

 Arguments

0.33

arguments

0.33

arg

0.33

 Argument

0.31

Arguments

0.30

args

0.30

Arg

0.30

Activations Density 0.412%

technical terms and phrases related to programming functions and arguments

No Comments

No Known Activations