INDEX

Explanations

punctuation marks and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

embro

-0.16

anford

-0.16

vox

-0.15

ÙĦÙģ

-0.15

æĭĶ

-0.14

 Alarm

-0.14

prite

-0.14

ang

-0.14

ank

-0.14

uff

-0.14

POSITIVE LOGITS

aron

0.14

 Commod

0.14

_KeyPress

0.14

_DH

0.14

mbH

0.14

)\<

0.14

Culture

0.13

ÑĢÐ°Ð¶

0.13

ometr

0.13

¢åįķ

0.13

Activations Density 0.398%

punctuation marks and symbols

No Comments

No Known Activations