INDEX

Explanations

elements related to graphical representations and figures in scientific documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

esco

-0.16

arty

-0.15

ensi

-0.14

ower

-0.13

apy

-0.13

 worlds

-0.13

 values

-0.13

 Lamar

-0.13

 èĥ

-0.13

ollapse

-0.13

POSITIVE LOGITS

nonnull

0.15

å±±å¸Ĥ

0.15

ount

0.14

OFFSET

0.14

ferred

0.14

Äįku

0.14

 NodeList

0.14

indo

0.14

Activations Density 0.008%

elements related to graphical representations and figures in scientific documentation

No Comments

No Known Activations