INDEX

Explanations

references to historical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ihan

-0.17

to

-0.16

/he

-0.16

-0.15

 Modern

-0.15

hol

-0.15

on

-0.14

 anymore

-0.13

ex

-0.13

POSITIVE LOGITS

à¥ĭà¤ĸ

0.18

/current

0.17

ÚĨÙĩ

0.16

usan

0.16

iben

0.16

stery

0.16

ssp

0.15

cobra

0.15

rips

0.15

 ÄĮer

0.15

Activations Density 0.017%

references to historical significance

No Comments

No Known Activations