INDEX

Explanations

terms related to nuance and complexity in social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

hurst

-0.17

oeff

-0.15

ing

-0.15

uish

-0.15

plr

-0.14

 Robbins

-0.14

uil

-0.14

ea

-0.14

avin

-0.14

chn

-0.14

POSITIVE LOGITS

ANCES

0.22

anced

0.22

ances

0.22

clide

0.20

ance

0.19

erosis

0.19

íħĶ

0.18

ANCE

0.17

Nu

0.17

ANCED

0.17

Activations Density 0.017%

terms related to nuance and complexity in social interactions

No Comments

No Known Activations