INDEX

Explanations

specific governmental or organizational entities and trademarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

á»ĳc

-0.15

quo

-0.15

ãĥ

-0.15

igo

-0.14

 perman

-0.14

lessly

-0.14

lic

-0.14

lice

-0.14

IMIT

-0.13

zed

-0.13

POSITIVE LOGITS

ENCED

0.16

/Peak

0.15

 onResponse

0.14

Ler

0.14

 neust

0.14

IDb

0.14

arp

0.14

/Runtime

0.13

_then

0.13

.ibatis

0.13

Activations Density 0.009%

specific governmental or organizational entities and trademarks

No Comments

No Known Activations