INDEX

Explanations

mentions of the word "Sel" and its variations, indicating a focus on hierarchical or organizational terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

dre

-0.16

é¥

-0.15

illard

-0.15

odate

-0.15

ÃŃv

-0.14

rikes

-0.14

-Semit

-0.13

INGLE

-0.13

fall

-0.13

ilater

-0.13

POSITIVE LOGITS

Ã§uk

0.24

inux

0.23

bst

0.21

vester

0.20

ÐµÐºÑĤÐ¸Ð²

0.20

wyn

0.18

BST

0.17

anik

0.17

hurst

0.17

engkap

0.17

Activations Density 0.012%

mentions of the word "Sel" and its variations, indicating a focus on hierarchical or organizational terms

No Comments

No Known Activations