INDEX

Explanations

programming syntax and elements related to list and data structure manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

uggage

-0.16

able

-0.15

å¾ĭ

-0.15

ander

-0.15

OMEM

-0.15

udit

-0.14

ed

-0.13

ulo

-0.13

POSITIVE LOGITS

ltk

0.14

à¤¾à¤²à¤¨

0.14

iena

0.14

ê·Ģ

0.14

pora

0.13

aload

0.13

iry

0.13

ataka

0.13

xima

0.13

.generated

0.13

Activations Density 0.102%

programming syntax and elements related to list and data structure manipulation

No Comments

No Known Activations