INDEX

Explanations

structures related to figures and captions within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Î®ÏĤ

-0.16

 Serge

-0.15

Ø¨ÙĬÙĨ

-0.14

voke

-0.14

;element

-0.14

 Ferry

-0.14

eczy

-0.13

ģ

-0.13

lÃ½

-0.13

execute

-0.13

POSITIVE LOGITS

safe

0.15

ows

0.15

Safe

0.15

 Safe

0.14

 tÆ°á»£ng

0.14

TRS

0.14

OW

0.14

iras

0.14

am

0.14

ÑĢÑĥÑĩ

0.13

Activations Density 0.043%

structures related to figures and captions within a document

No Comments

No Known Activations