INDEX

Explanations

references to the first element or child in a sequence or collection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ÅĤo

-0.15

ingo

-0.15

ensis

-0.15

 cins

-0.15

incr

-0.14

TargetException

-0.14

vic

-0.14

ede

-0.14

baar

-0.14

.removeListener

-0.14

POSITIVE LOGITS

oop

0.17

 Wikip

0.14

Lit

0.14

æ°ĳ

0.14

omm

0.14

arp

0.14

owie

0.13

woods

0.13

oundingBox

0.13

 {{↵

0.13

Activations Density 0.118%

references to the first element or child in a sequence or collection

No Comments

No Known Activations