INDEX

Explanations

references to APIs and programming constructs in technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

à¥Ģà¤«

-0.18

åĬŀåħ¬

-0.17

jom

-0.17

rossover

-0.16

alet

-0.15

IIIK

-0.14

_CHARS

-0.14

Ð¾Ð¼Ñĸ

-0.14

_GAIN

-0.14

_ios

-0.14

POSITIVE LOGITS

ippi

0.17

embro

0.17

ada

0.17

Ð¾ÑĢÐ¾Ð´

0.17

lag

0.17

Jer

0.15

lags

0.15

sey

0.15

adas

0.15

iana

0.15

Activations Density 0.014%

references to APIs and programming constructs in technical documents

No Comments

No Known Activations