INDEX

Explanations

programming constructs and syntax related to numerical operations or data handling

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.16

enstein

-0.15

airs

-0.15

éłĥ

-0.15

olf

-0.14

/cms

-0.14

traction

-0.14

ettes

-0.14

iao

-0.14

POSITIVE LOGITS

cal

0.17

abay

0.17

idl

0.15

ikh

0.15

iber

0.14

 ì¼ĢìĿ´

0.14

ADOW

0.14

aky

0.14

Fight

0.14

WISE

0.13

Activations Density 0.053%

programming constructs and syntax related to numerical operations or data handling

No Comments

No Known Activations