INDEX

Explanations

keywords related to legal and historical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aris

-0.16

.scalablytyped

-0.16

asa

-0.16

asad

-0.15

venue

-0.15

inux

-0.14

ÑĤÐ¾Ð¼

-0.14

.Sin

-0.14

áº¿n

-0.14

opot

-0.14

POSITIVE LOGITS

rides

0.17

 subject

0.17

xico

0.16

ãĤ¹ãĤ¿ãĥ¼

0.15

ral

0.15

bject

0.15

 Grinder

0.14

Rub

0.14

rub

0.14

 rope

0.14

Activations Density 0.058%

keywords related to legal and historical documentation

No Comments

No Known Activations