INDEX

Explanations

attributes and dimensions related to graphical elements in code

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

loon

-0.17

strup

-0.15

ipt

-0.15

edla

-0.15

stell

-0.15

oll

-0.14

antu

-0.14

Hel

-0.14

aÅŁ

-0.14

 Genel

-0.14

POSITIVE LOGITS

bench

0.16

apore

0.15

erview

0.15

iou

0.14

gs

0.14

uers

0.14

 benchmarks

0.14

 kind

0.14

yne

0.13

 equivalence

0.13

Activations Density 0.054%

attributes and dimensions related to graphical elements in code

No Comments

No Known Activations