INDEX

Explanations

terms related to scanning and measurement techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Haut

-0.16

estroy

-0.15

stands

-0.15

acomment

-0.15

scalar

-0.14

kah

-0.14

errupt

-0.14

stand

-0.14

lijke

-0.14

standing

-0.14

POSITIVE LOGITS

sdale

0.22

warz

0.21

orama

0.19

andin

0.18

crow

0.17

atology

0.17

izo

0.16

çĽ®

0.16

izoph

0.16

adding

0.16

Activations Density 0.055%

terms related to scanning and measurement techniques

No Comments

No Known Activations