INDEX

Explanations

keywords related to proteins and their various attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

agate

-0.16

ifer

-0.15

irie

-0.15

elly

-0.14

Fri

-0.14

ãĥªãĥ¼

-0.14

rawn

-0.14

Bau

-0.13

issa

-0.13

pie

-0.13

POSITIVE LOGITS

entials

0.14

ëĤĺë¬´

0.14

utr

0.14

ellungen

0.14

nap

0.14

ossier

0.13

wyn

0.13

Â´:

0.13

(Pos

0.13

 Mattis

0.13

Activations Density 0.023%

keywords related to proteins and their various attributes

No Comments

No Known Activations