INDEX

Explanations

negative outcomes or disclaimers related to product usage or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

utenberg

-0.16

ãĤ¤ãĤº

-0.16

-0.15

ìĩ

-0.14

æ³¨

-0.14

jon

-0.14

.decorate

-0.14

 Brands

-0.13

jun

-0.13

Fil

-0.13

POSITIVE LOGITS

çĽŁ

0.15

reau

0.15

lear

0.14

.Standard

0.14

orce

0.14

eto

0.14

uais

0.14

arious

0.14

_cast

0.13

 Consolid

0.13

Activations Density 0.045%

negative outcomes or disclaimers related to product usage or services

No Comments

No Known Activations