INDEX

Explanations

words indicating legal terms or proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.createClass

-0.15

Gut

-0.15

Lis

-0.15

 intern

-0.14

nan

-0.14

Gow

-0.14

typings

-0.14

hek

-0.14

 grace

-0.14

 Pound

-0.13

POSITIVE LOGITS

ãĥ©ãĥĥãĤ¯

0.17

.Rollback

0.16

AAF

0.16

ugo

0.15

onical

0.15

ddy

0.14

egov

0.14

eum

0.14

geois

0.14

Wizard

0.14

Activations Density 0.004%

words indicating legal terms or proceedings

No Comments

No Known Activations