INDEX

Explanations

keywords or phrases relating to specific subjects or entities

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

tach

-0.15

íİ

-0.14

 Raven

-0.14

.atomic

-0.14

ear

-0.14

@Id

-0.14

 Incontri

-0.14

.snap

-0.13

tek

-0.13

POSITIVE LOGITS

atten

0.14

 ladies

0.14

lesen

0.14

vÅ¯

0.14

levant

0.14

unik

0.13

Unc

0.13

hire

0.13

 sharedApplication

0.13

 frameborder

0.13

Activations Density 0.004%

keywords or phrases relating to specific subjects or entities

No Comments

No Known Activations