INDEX

Explanations

terms related to existence and the concept of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

atura

-0.18

standing

-0.15

iz

-0.15

ille

-0.15

ebb

-0.15

echa

-0.15

oenix

-0.14

owl

-0.14

eb

-0.14

hausen

-0.14

POSITIVE LOGITS

entially

0.28

ential

0.25

entials

0.19

äºİ

0.17

ence

0.17

 Exists

0.15

$MESS

0.15

ÏįÏĢ

0.15

Ø©

0.14

ent

0.14

Activations Density 0.045%

terms related to existence and the concept of being

No Comments

No Known Activations