INDEX

Explanations

phrases or references to frontline roles or positions

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

zap

-0.15

ucc

-0.14

thic

-0.14

estone

-0.14

 (*((

-0.14

 Joyce

-0.14

erty

-0.14

pekt

-0.14

 éĸ¢

-0.14

POSITIVE LOGITS

iers

0.23

 burner

0.20

liner

0.20

 porch

0.19

 office

0.19

isp

0.19

-office

0.18

/front

0.18

-line

0.18

Activations Density 0.013%

phrases or references to frontline roles or positions

No Comments

No Known Activations

phrases or references to frontline roles or positions

No Comments

No Known Activations