INDEX

Explanations

HTML elements and structure in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

enko

-0.16

Sat

-0.16

ET

-0.16

 Unified

-0.15

andi

-0.15

rou

-0.15

sat

-0.14

rop

-0.14

aux

-0.14

POSITIVE LOGITS

ãĥ¼ãĥł

0.21

ãĥ¼ãĥ³

0.18

 addCriterion

0.18

 class

0.17

><

0.17

dete

0.17

.vaadin

0.16

indy

0.15

inox

0.15

ÄįnÃŃk

0.15

Activations Density 0.020%

HTML elements and structure in the document

No Comments

No Known Activations