INDEX

Explanations

tags associated with various topics or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

spect

-0.15

Entering

-0.14

ering

-0.14

 pParent

-0.14

æº

-0.14

lineEdit

-0.14

anca

-0.13

.updateDynamic

-0.13

 è¯¦æĥħ

-0.13

æŁ³

-0.13

POSITIVE LOGITS

Filed

0.24

ged

0.21

 Filed

0.17

ksen

0.17

ired

0.16

wa

0.16

iterals

0.16

istra

0.15

ussen

0.15

Activations Density 0.004%

tags associated with various topics or categories

No Comments

No Known Activations