INDEX

Explanations

words related to achievement and success

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

rr

-0.20

enstein

-0.16

ìĥģ

-0.15

rh

-0.15

pared

-0.15

nil

-0.15

ady

-0.15

argout

-0.14

ì±Ħ

-0.14

alytics

-0.14

POSITIVE LOGITS

ving

0.42

vers

0.41

ved

0.37

ves

0.34

ver

0.34

vable

0.34

vements

0.34

ve

0.32

vement

0.31

VER

0.29

Activations Density 0.022%

words related to achievement and success

No Comments

No Known Activations