INDEX

Explanations

mentions of legal proceedings and related evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 lawsuit

-0.17

 lawsuits

-0.17

assel

-0.15

Tin

-0.15

 pobl

-0.14

lier

-0.14

arro

-0.14

vej

-0.14

umberland

-0.13

 Retro

-0.13

POSITIVE LOGITS

 Crown

0.31

 crown

0.29

 Directions

0.21

PACE

0.21

mag

0.21

 directions

0.20

 Disclosure

0.19

Directions

0.19

 undef

0.19

ãĥ³ãĤ°ãĥ«

0.18

Activations Density 0.042%

mentions of legal proceedings and related evidence

No Comments

No Known Activations