INDEX

Explanations

past tense verbs indicating experience and involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

oyer

-0.16

å±¥

-0.16

mpp

-0.15

ener

-0.15

athlete

-0.15

ledged

-0.14

indsight

-0.14

ignite

-0.14

_tac

-0.14

erf

-0.14

POSITIVE LOGITS

 involved

0.31

 employed

0.28

 part

0.24

employed

0.21

 president

0.20

 active

0.20

 responsible

0.19

 invol

0.19

 editor

0.19

 engaged

0.19

Activations Density 0.080%

past tense verbs indicating experience and involvement

No Comments

No Known Activations