INDEX

Explanations

issues related to accountability and responsibility in various contexts

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

ieri

-0.16

 Stern

-0.15

ward

-0.14

Ð¾Ð½Ðµ

-0.14

Coh

-0.14

 station

-0.14

esub

-0.13

ãĥ³ãĥĳ

-0.13

Ð¾Ð»ÑĮ

-0.13

iro

-0.13

POSITIVE LOGITS

andas

0.18

emer

0.16

lette

0.16

endir

0.16

Å¡e

0.16

usta

0.16

enance

0.15

amt

0.15

lek

0.14

NAL

0.14

Activations Density 0.325%

issues related to accountability and responsibility in various contexts

No Comments

No Known Activations