INDEX

Explanations

structured information and announcements in a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ATYPE

-0.17

ual

-0.16

let

-0.15

zig

-0.15

fully

-0.15

erg

-0.15

qual

-0.15

TRGL

-0.14

ado

-0.14

ig

-0.14

POSITIVE LOGITS

'S

0.21

’S

0.21

ING

0.16

phinx

0.16

ER

0.15

AS

0.15

Ä°

0.15

etine

0.15

IT

0.15

CH

0.15

Activations Density 0.532%

structured information and announcements in a formal context

No Comments

No Known Activations

structured information and announcements in a formal context

No Comments

No Known Activations