INDEX

Explanations

terms related to screenshots and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

addin

-0.17

obre

-0.15

 Ware

-0.14

å¹²

-0.14

ORB

-0.14

rees

-0.14

obao

-0.14

urence

-0.14

aggi

-0.13

aggio

-0.13

POSITIVE LOGITS

ÄįÃ¡st

0.16

lÃ½

0.15

levision

0.14

itious

0.14

 dividing

0.14

 Pills

0.14

pcf

0.14

cesso

0.14

 Broad

0.14

ÑģÑĤÑĢÐ¾Ð²

0.14

Activations Density 0.013%

terms related to screenshots and their usage

No Comments

No Known Activations