INDEX

Explanations

number sequences and large numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

uman

-0.16

ä¸ĸç´Ģ

-0.16

umin

-0.15

onu

-0.15

erez

-0.14

 Millionen

-0.14

Ð±Ð¾ÑĤ

-0.13

ou

-0.13

opp

-0.13

ens

-0.13

POSITIVE LOGITS

ths

0.24

-plus

0.21

mAh

0.18

+</

0.17

amoto

0.16

0.15

-strong

0.15

uffs

0.15

nbsp

0.15

0.14

Activations Density 0.087%

number sequences and large numerical values

No Comments

No Known Activations