INDEX

Explanations

patterns of numerical data and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

urette

-0.17

ileo

-0.16

osit

-0.15

vala

-0.15

YLE

-0.15

pur

-0.14

Äįet

-0.14

andelier

-0.14

rokes

-0.14

ilon

-0.14

POSITIVE LOGITS

inalg

0.14

enheim

0.14

odyn

0.14

kul

0.14

iez

0.13

,:,

0.13

DAY

0.13

 Freed

0.13

 HEAP

0.13

bara

0.13

Activations Density 0.067%

patterns of numerical data and codes

No Comments

No Known Activations