INDEX

Explanations

time-related details and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

anka

-0.17

olicit

-0.16

zung

-0.15

ë³µ

-0.15

 humid

-0.15

åĩ¡

-0.15

avra

-0.14

anca

-0.14

aina

-0.14

gr

-0.14

POSITIVE LOGITS

 omap

0.15

oval

0.14

eshire

0.14

ÎµÎ¹Î¿

0.14

lique

0.14

UY

0.14

aign

0.13

intree

0.13

.Batch

0.13

é«

0.13

Activations Density 0.022%

time-related details and events

No Comments

No Known Activations