INDEX

Explanations

symbols or special characters used in digital communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 afterward

-0.17

 said

-0.17

said

-0.16

seau

-0.16

 subsequent

-0.15

ListGroup

-0.14

 thereafter

-0.14

 afterwards

-0.14

 capture

-0.13

 believed

-0.13

POSITIVE LOGITS

å±ķç¤º

0.19

 mostra

0.19

 supplied

0.18

 Reve

0.18

 demonstrate

0.17

 shows

0.17

 reveals

0.17

zeigt

0.17

 revealed

0.17

 provided

0.17

Activations Density 0.023%

symbols or special characters used in digital communication

No Comments

No Known Activations