INDEX

Explanations

references to legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 prim

-0.16

itzer

-0.15

ÑĥÑĪ

-0.15

sah

-0.15

cr

-0.15

NTN

-0.14

lers

-0.14

uttle

-0.14

lle

-0.14

aver

-0.14

POSITIVE LOGITS

 RedirectTo

0.15

gree

0.14

ESCO

0.14

.FontStyle

0.14

.vaadin

0.14

Civ

0.14

inea

0.14

orrect

0.13

/Branch

0.13

":[{↵

0.13

Activations Density 0.025%

references to legal cases

No Comments

No Known Activations