INDEX

Explanations

subjective statements about people's experiences and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

amik

-0.17

zcze

-0.17

astos

-0.15

ãĥ¡ãĥ©

-0.15

amarin

-0.14

otta

-0.14

.UnitTesting

-0.14

htags

-0.13

èĥ

-0.13

rapper

-0.13

POSITIVE LOGITS

Ø¦Ø©

0.14

HV

0.14

 Wich

0.14

ãĥ¼ãĥķ

0.14

 sine

0.14

¶Į

0.14

 Hess

0.13

hv

0.13

lob

0.13

Activations Density 0.056%

subjective statements about people's experiences and actions

No Comments

No Known Activations