INDEX

Explanations

references to annual reports and related administrative content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÙĥØ±Ø©

-0.17

ocl

-0.15

é¬

-0.14

ammer

-0.14

oine

-0.14

ÙģØ§ÙĦ

-0.13

Ð³Ð»

-0.13

ãĥ³ãĥĸ

-0.13

ìĭ¸

-0.13

curity

-0.13

POSITIVE LOGITS

 report

0.35

 reports

0.29

 Report

0.28

åł±åĳĬ

0.24

Report

0.24

report

0.24

.report

0.24

 REPORT

0.23

(report

0.23

æĬ¥åĳĬ

0.23

Activations Density 0.075%

references to annual reports and related administrative content

No Comments

No Known Activations