INDEX

Explanations

mathematical expressions and notations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

deen

-0.17

zl

-0.16

jvu

-0.16

oundation

-0.14

à¥ĩà¤¦à¤¨

-0.14

alance

-0.14

-dismiss

-0.14

AMAGE

-0.14

^K

-0.14

OwnProperty

-0.14

POSITIVE LOGITS

ritch

0.15

agate

0.15

ison

0.14

isin

0.14

 Loft

0.14

ller

0.14

ÙĨØ´

0.14

oner

0.14

SetTitle

0.13

icter

0.13

Activations Density 0.114%

mathematical expressions and notations within the text

No Comments

No Known Activations