INDEX

Explanations

structured formats and references in academic writing

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

ako

-0.17

vers

-0.16

rels

-0.16

Backdrop

-0.15

 specificity

-0.15

¼

-0.14

cÃ©

-0.14

ity

-0.14

POSITIVE LOGITS

 rÃ¡p

0.17

âĢ¦↵↵↵

0.16

@brief

0.15

¬

0.15

 sokak

0.15

éºĹ

0.15

vailable

0.14

Î´Ïİ

0.14

abinet

0.14

ibraries

0.14

Activations Density 0.034%

structured formats and references in academic writing

No Comments

No Known Activations