INDEX

Explanations

numerical identifiers or codes

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

ey

-0.18

ening

-0.18

igned

-0.17

ause

-0.16

ldr

-0.16

ÑĥÐºÐ¸

-0.16

ery

-0.15

.au

-0.15

aus

-0.15

 latter

-0.15

POSITIVE LOGITS

ëĭ¤

0.19

clair

0.17

ochond

0.15

IVE

0.15

à¸£à¸²à¸Ĭ

0.15

oyal

0.15

0.14

ÑĮÐºÐ¾

0.14

ocup

0.14

ively

0.14

Activations Density 0.124%

numerical identifiers or codes

No Comments

No Known Activations