INDEX

Explanations

references to radiators and related components in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

andest

-0.19

UAL

-0.17

vj

-0.16

ÅŁehir

-0.14

ocide

-0.14

jvu

-0.14

braco

-0.14

 Williamson

-0.14

velope

-0.14

encia

-0.14

POSITIVE LOGITS

hra

0.16

0.15

arf

0.15

xx

0.14

oter

0.14

hsi

0.14

Ã©g

0.14

er

0.14

ls

0.14

Activations Density 0.033%

references to radiators and related components in technical contexts

No Comments

No Known Activations