INDEX

Explanations

occurrences of the name "Cord" or related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

eyed

-0.17

berman

-0.17

aku

-0.16

.slim

-0.16

Subviews

-0.16

bourg

-0.16

usercontent

-0.15

erties

-0.14

qa

-0.14

ieties

-0.14

POSITIVE LOGITS

ially

0.24

oba

0.22

uro

0.21

cord

0.20

ovan

0.19

oned

0.19

oning

0.18

ial

0.16

 cord

0.16

ridge

0.16

Activations Density 0.009%

occurrences of the name "Cord" or related variations

No Comments

No Known Activations