INDEX

Explanations

words related to legal proceedings and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

abet

-0.17

gni

-0.15

iec

-0.15

 GOODMAN

-0.15

 GÃ¼l

-0.15

 Brooke

-0.14

orie

-0.14

eler

-0.14

ulle

-0.14

onas

-0.14

POSITIVE LOGITS

 earlier

0.22

 previous

0.20

 Earlier

0.19

 previously

0.18

 Previous

0.16

Previously

0.16

Earlier

0.16

 Previously

0.16

oba

0.16

previous

0.15

Activations Density 0.245%

words related to legal proceedings and actions

No Comments

No Known Activations