INDEX

Explanations

references to educational and research institutions, particularly in the fields of health, science, and policy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

æ°ı

-0.16

emd

-0.16

udic

-0.14

Łèĥ½

-0.14

indow

-0.14

çĳ

-0.14

stitutions

-0.14

ensa

-0.14

auses

-0.14

alars

-0.14

POSITIVE LOGITS

 within

0.22

within

0.20

 thuá»Ļc

0.18

 Within

0.17

Within

0.17

iggins

0.17

at

0.16

igar

0.15

 housed

0.15

Activations Density 0.122%

references to educational and research institutions, particularly in the fields of health, science, and policy

No Comments

No Known Activations