INDEX

Explanations

references to schedules or planned events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

age

-0.18

ason

-0.16

nage

-0.16

 scratch

-0.16

ahir

-0.15

 tide

-0.15

ilden

-0.14

 gross

-0.14

äºİ

-0.14

 ring

-0.14

POSITIVE LOGITS

ulers

0.18

íĳľ

0.17

ipment

0.16

ULER

0.16

FTER

0.15

NDAR

0.15

Ð¼Ð¾ÑĢ

0.15

izo

0.15

ORY

0.15

istrovstvÃŃ

0.15

Activations Density 0.029%

references to schedules or planned events

No Comments

No Known Activations