INDEX

Explanations

numerical identifiers or references, particularly in the context of academic or formal citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ed

-0.25

iw

-0.20

ths

-0.18

lane

-0.18

Ð¸Ñħ

-0.17

ÑģÑı

-0.16

ex

-0.16

umble

-0.15

in

-0.15

POSITIVE LOGITS

st

0.34

/XMLSchema

0.19

ÏĤ

0.18

çħ§

0.18

ë²Ī

0.17

radan

0.16

igin

0.16

iden

0.15

wan

0.15

lest

0.15

Activations Density 0.180%

numerical identifiers or references, particularly in the context of academic or formal citations

No Comments

No Known Activations