INDEX

Explanations

significant or impactful occurrences and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÏĦÎ¹Îº

-0.17

wargs

-0.17

panic

-0.16

preci

-0.16

ÏģÎ¹Î½

-0.15

uld

-0.15

çĽ®çļĦ

-0.15

-Ñı

-0.15

jours

-0.15

/releases

-0.15

POSITIVE LOGITS

0.19

ocom

0.17

amo

0.15

 Burke

0.15

 Gilbert

0.15

 mend

0.14

 versus

0.14

 Bend

0.14

 audible

0.14

å¾¡

0.14

Activations Density 0.120%

significant or impactful occurrences and concepts

No Comments

No Known Activations