INDEX

Explanations

phrases indicating the presence of relationships or associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 fact

-0.16

enko

-0.14

igg

-0.14

urn

-0.14

ifo

-0.14

æĢ»

-0.13

 turno

-0.13

per

-0.13

or

-0.13

POSITIVE LOGITS

 regards

0.22

 regard

0.20

sdale

0.20

 gusto

0.17

lÃ¡n

0.17

ohon

0.16

inspace

0.16

hold

0.16

QRST

0.16

ersh

0.16

Activations Density 0.198%

phrases indicating the presence of relationships or associations

No Comments

No Known Activations