INDEX

Explanations

questions related to programming inquiries and technical instructions

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

rack

-0.14

Lid

-0.14

UIL

-0.14

ÙĪÙĤ

-0.14

 puzzle

-0.14

ushi

-0.14

Pet

-0.13

Ice

-0.13

fff

-0.13

POSITIVE LOGITS

ÑĮÐµ

0.17

ascus

0.16

elerik

0.15

ampo

0.15

ennen

0.15

Ã©rc

0.15

Ã©rÃ©

0.14

CRET

0.14

lyph

0.14

swick

0.14

Activations Density 0.280%

questions related to programming inquiries and technical instructions

No Comments

No Known Activations