INDEX

Explanations

numeric references and timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

nano

-0.16

ingen

-0.15

Pin

-0.15

-caret

-0.15

ÙĦØ§ØŃ

-0.14

 Presence

-0.14

Nan

-0.13

nan

-0.13

erto

-0.13

Gro

-0.13

POSITIVE LOGITS

Kah

0.15

pch

0.15

abinet

0.14

ant

0.14

 Mahm

0.14

 Bain

0.13

&type

0.13

KA

0.13

uest

0.13

0.12

Activations Density 0.000%

numeric references and timestamps

No Comments

No Known Activations