INDEX

Explanations

mentions of radio

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

ment

-0.24

ments

-0.20

by

-0.18

tings

-0.18

ernaut

-0.18

rou

-0.17

ust

-0.17

mente

-0.17

baz

-0.17

ryo

-0.16

POSITIVE LOGITS

active

0.25

therapy

0.25

activity

0.25

thon

0.23

frequency

0.22

 stations

0.21

actively

0.20

 station

0.20

 Shack

0.18

 waves

0.18

Activations Density 0.011%

mentions of radio

No Comments

No Known Activations