INDEX

Explanations

numerical values and parameters within code snippets

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

aterangepicker

-0.15

 addCriterion

-0.15

inha

-0.14

 Lifetime

-0.14

.Logic

-0.14

((-

-0.14

velt

-0.14

 Ð±Ð°Ðº

-0.14

 hale

-0.14

licant

-0.14

POSITIVE LOGITS

VAS

0.17

anou

0.15

Ð½Ñı

0.15

nul

0.14

AMB

0.14

azio

0.14

try

0.14

amb

0.14

NOP

0.14

 philosoph

0.13

Activations Density 0.040%

numerical values and parameters within code snippets

No Comments

No Known Activations