INDEX

Explanations

words related to infrastructure and organizational elements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

alian

-0.17

OfString

-0.16

chk

-0.15

 hierarchy

-0.15

getic

-0.14

oxide

-0.14

eg

-0.14

uder

-0.14

chl

-0.14

POSITIVE LOGITS

ippo

0.16

 Karlov

0.15

Â§Ãĥ

0.15

 TMPro

0.14

estead

0.14

/uploads

0.14

antino

0.14

osemite

0.13

 createSelector

0.13

 Fucked

0.13

Activations Density 0.238%

words related to infrastructure and organizational elements

No Comments

No Known Activations