INDEX

Explanations

statistical information and numerical data regarding studies or surveys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ese

-0.17

uros

-0.16

ues

-0.15

ibus

-0.15

ufen

-0.15

$MESS

-0.14

nam

-0.14

reh

-0.14

uche

-0.14

sek

-0.14

POSITIVE LOGITS

asaki

0.17

etooth

0.17

raki

0.15

gst

0.14

dej

0.14

 amongst

0.14

á»ĳng

0.14

Î¼ÎŃ

0.13

 borr

0.13

Bat

0.13

Activations Density 0.045%

statistical information and numerical data regarding studies or surveys

No Comments

No Known Activations