INDEX

Explanations

significant numerical values or indicators of quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

enis

-0.18

eries

-0.17

ej

-0.15

PEC

-0.14

ml

-0.14

eps

-0.14

iej

-0.14

 Belgian

-0.13

 Hack

-0.13

ÑĢÐ¾ÑĪ

-0.13

POSITIVE LOGITS

orsk

0.15

Bri

0.15

emat

0.15

Mocks

0.14

apter

0.14

Ã¼re

0.14

.BorderFactory

0.14

Ymd

0.14

ypse

0.14

gth

0.14

Activations Density 0.007%

significant numerical values or indicators of quantity

No Comments

No Known Activations