INDEX

Explanations

numerical values and their associations with years or other significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ipple

-0.19

antz

-0.17

membership

-0.14

§

-0.14

enez

-0.13

 InputStreamReader

-0.13

aries

-0.13

ilde

-0.13

iless

-0.13

ngth

-0.13

POSITIVE LOGITS

Ú©Ø§Øª

0.15

ino

0.15

ESA

0.15

ÄĻd

0.14

igo

0.14

 Tato

0.14

 Rossi

0.14

gre

0.14

ìļ´ëį°

0.13

illet

0.13

Activations Density 0.083%

numerical values and their associations with years or other significant events

No Comments

No Known Activations