INDEX

Explanations

expressions of personal feelings and emotional responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

emez

-0.15

ÃŃda

-0.15

vailability

-0.15

eyin

-0.15

MOTE

-0.15

rema

-0.14

regor

-0.14

ALSE

-0.14

ONO

-0.14

pering

-0.14

POSITIVE LOGITS

 feel

0.23

 uncomfortable

0.23

 aware

0.23

 want

0.23

sad

0.21

 question

0.20

 proud

0.20

gig

0.20

 laugh

0.19

 comfortable

0.19

Activations Density 0.037%

expressions of personal feelings and emotional responses

No Comments

No Known Activations