INDEX

Explanations

instances of the articles "a" and "an."

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

-urlencoded

-0.16

prung

-0.15

éĿ©

-0.15

nx

-0.14

gado

-0.14

ORIA

-0.14

redo

-0.14

cer

-0.14

çķ¥

-0.14

entina

-0.14

POSITIVE LOGITS

angep

0.16

unga

0.15

isz

0.14

Ð½Ð°Ñħ

0.14

Ã¤Ã¤n

0.14

Ð±Ñĭ

0.14

hazi

0.13

endencies

0.13

tas

0.13

ODB

0.13

Activations Density 0.274%

instances of the articles "a" and "an."

No Comments

No Known Activations