INDEX

Explanations

instances of public scrutiny and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ERSHEY

-0.15

ALER

-0.14

ìĨĮê°ľ

-0.14

 STRICT

-0.13

stud

-0.13

 Dabei

-0.13

ched

-0.13

 Year

-0.13

ubs

-0.13

POSITIVE LOGITS

 neither

0.23

 representatives

0.21

 sources

0.20

 Neither

0.20

Neither

0.20

 spokes

0.18

 yesterday

0.18

 contacted

0.17

 documents

0.17

 subsequent

0.16

Activations Density 0.151%

instances of public scrutiny and accountability

No Comments

No Known Activations