INDEX

Explanations

references to articles and news titles related to events or reports

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

oki

-0.16

ichert

-0.15

 subject

-0.15

 target

-0.15

éĿ

-0.14

 åĥ

-0.14

_anchor

-0.14

 Anch

-0.14

Ä±ÄŁÄ±

-0.14

Łèĥ½

-0.14

POSITIVE LOGITS

0.17

icit

0.16

ime

0.15

IME

0.15

ÑģÑıÑĤ

0.14

ENDOR

0.14

apat

0.14

afil

0.14

ð

0.14

ett

0.13

Activations Density 0.361%

references to articles and news titles related to events or reports

No Comments

No Known Activations