INDEX

Explanations

references to various types of tests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

zon

-0.20

aign

-0.18

resi

-0.17

reso

-0.17

yps

-0.16

zego

-0.16

kins

-0.15

ÑĢÐ°ÑĤÐ¸

-0.15

heid

-0.15

getElementsByTagName

-0.15

POSITIVE LOGITS

ãĤ¦ãĥĪ

0.20

acular

0.15

tera

0.15

0.14

 Ingram

0.14

illa

0.14

kla

0.14

 Individuals

0.14

avar

0.14

_FOREACH

0.14

Activations Density 0.025%

references to various types of tests

No Comments

No Known Activations