INDEX

Explanations

components and features related to products and equipment

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

 string

-0.18

 strings

-0.17

-string

-0.17

itel

-0.15

ribbon

-0.15

 ribbon

-0.15

 String

-0.15

adden

-0.15

 Noel

-0.15

_trim

-0.14

POSITIVE LOGITS

 Crosby

0.20

bel

0.19

prus

0.19

 fall

0.18

 multiplic

0.18

 kern

0.17

pul

0.17

 spectra

0.17

spect

0.17

 Spect

0.16

Activations Density 0.022%

components and features related to products and equipment

No Comments

No Known Activations