INDEX

Explanations

references to digital services and connectivity issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cgi

-0.15

upertino

-0.15

ertext

-0.15

Gim

-0.15

 Dame

-0.14

å¤§åħ¨

-0.14

à¸·à¸Ńà¸Ķ

-0.14

 Chain

-0.13

ssp

-0.13

.factor

-0.13

POSITIVE LOGITS

 cable

0.44

 Cable

0.43

 Charter

0.31

 Comcast

0.28

 Dire

0.27

 Dish

0.25

Cox

0.25

 cables

0.24

 Spectrum

0.24

 fiber

0.23

Activations Density 0.053%

references to digital services and connectivity issues

No Comments

No Known Activations