INDEX

Explanations

punctuations and formatting indicators, particularly around biographical information

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

 éĦ

-0.16

quer

-0.14

bakan

-0.14

arrow

-0.14

ilha

-0.14

Ã¡c

-0.13

á»ĥn

-0.13

lagen

-0.13

hape

-0.13

oshi

-0.13

POSITIVE LOGITS

 talking

0.23

 Talking

0.21

Talking

0.20

 similarly

0.19

CAP

0.17

Caption

0.15

sources

0.14

 Similarly

0.14

 talks

0.14

Scroll

0.14

Activations Density 0.008%

punctuations and formatting indicators, particularly around biographical information

No Comments

No Known Activations