INDEX

Explanations

references to external sources or frameworks in context of programming or system operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ð²ÑĸÐ»ÑĮ

-0.15

.onDestroy

-0.14

ilog

-0.14

isk

-0.14

aylor

-0.14

imagin

-0.14

 Manning

-0.13

 è©³ç´°

-0.13

alore

-0.13

åĦĦ

-0.13

POSITIVE LOGITS

 upstream

0.15

kowski

0.15

 system

0.15

anza

0.14

cond

0.13

laws

0.13

apt

0.13

PRETTY

0.13

ìłľ

0.13

contest

0.13

Activations Density 0.088%

references to external sources or frameworks in context of programming or system operations

No Comments

No Known Activations