INDEX

Explanations

instances of the word "So" signaling a transition or emphasis in discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

niÄį

-0.15

igor

-0.15

memberOf

-0.15

epar

-0.14

rys

-0.14

eraÃ§Ã£o

-0.14

ummies

-0.14

lice

-0.14

udeau

-0.14

uisse

-0.14

POSITIVE LOGITS

oner

0.21

-called

0.20

onest

0.19

far

0.18

jaw

0.16

ìį¨

0.16

 UIStoryboard

0.15

oji

0.15

 forth

0.15

oooo

0.14

Activations Density 0.042%

instances of the word "So" signaling a transition or emphasis in discourse

No Comments

No Known Activations