INDEX

Explanations

indicators of code structure or data format attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

elow

-0.17

Î®Î½

-0.16

Handled

-0.14

Lub

-0.14

ertz

-0.14

 drowning

-0.14

rvÃ©

-0.13

iddi

-0.13

oenix

-0.13

esk

-0.13

POSITIVE LOGITS

.epam

0.17

isÃ©

0.15

ffen

0.14

 autof

0.14

kap

0.14

Baz

0.14

ritz

0.13

 Mandal

0.13

evin

0.13

hong

0.13

Activations Density 0.006%

indicators of code structure or data format attributes

No Comments

No Known Activations