INDEX

Explanations

expressions of gratitude and positive experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

argas

-0.15

pers

-0.15

mise

-0.15

inese

-0.14

ata

-0.14

vez

-0.14

untu

-0.14

omen

-0.14

yet

-0.14

llx

-0.13

POSITIVE LOGITS

icontrol

0.16

ìĿ´ìŀĲ

0.15

(DialogInterface

0.15

elial

0.14

="__

0.14

lide

0.14

clide

0.14

rog

0.13

 addCriterion

0.13

Activations Density 0.144%

expressions of gratitude and positive experiences

No Comments

No Known Activations