INDEX

Explanations

technical jargon and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÏĦÎ¿Îº

-0.15

Kos

-0.15

emas

-0.14

umo

-0.14

uur

-0.14

éľ

-0.14

arda

-0.14

alc

-0.14

å´ĩ

-0.13

elper

-0.13

POSITIVE LOGITS

wahl

0.16

agnost

0.15

semb

0.15

ãĥ³ãĥĩ

0.15

åı°

0.14

omat

0.14

ãģĹãģªãģĦ

0.14

ãĥ«ãĥī

0.14

 Mali

0.14

åĽ½äº§

0.14

Activations Density 0.006%

technical jargon and programming constructs

No Comments

No Known Activations