INDEX

Explanations

terms related to emotional well-being and social expectations

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

ew

-0.19

tered

-0.18

tle

-0.18

eral

-0.17

erson

-0.17

zers

-0.17

ively

-0.16

erc

-0.15

erville

-0.15

ìĽĶë¶ĢíĦ°

-0.15

POSITIVE LOGITS

naments

0.23

iginal

0.23

leans

0.23

izont

0.22

ãģ¹ãģį

0.21

tega

0.21

chestra

0.20

outines

0.19

IGIN

0.18

ìį¨

0.18

Activations Density 0.181%

terms related to emotional well-being and social expectations

No Comments

No Known Activations