INDEX

Explanations

identifiers or values associated with specific items or configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

upp

-0.15

arto

-0.14

pressor

-0.14

olla

-0.14

.Abstract

-0.14

Nad

-0.14

çª

-0.13

_prepare

-0.13

Pix

-0.13

 Wend

-0.13

POSITIVE LOGITS

zan

0.15

im

0.15

Ã¶g

0.13

ceph

0.13

 hete

0.13

 poil

0.13

 controvers

0.13

 Famous

0.13

ullo

0.13

ç¾

0.13

Activations Density 0.077%

identifiers or values associated with specific items or configurations

No Comments

No Known Activations