INDEX

Explanations

concepts related to informed consent, capacity, and the distinction between similar terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

META

-0.15

Eis

-0.15

isse

-0.14

geois

-0.14

iste

-0.14

CreateInfo

-0.14

abet

-0.13

emed

-0.13

-dark

-0.13

 port

-0.13

POSITIVE LOGITS

 distinction

0.18

 terms

0.17

.term

0.17

 distinct

0.16

_TERM

0.15

 difference

0.15

terms

0.15

 differences

0.15

 distinctions

0.15

/terms

0.15

Activations Density 0.085%

concepts related to informed consent, capacity, and the distinction between similar terms

No Comments

No Known Activations