INDEX

Explanations

phrases indicating areas, fields, or places of interest or focus

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.17

-0.15

/stretch

-0.14

ecz

-0.14

ka

-0.14

ura

-0.14

deen

-0.14

kov

-0.14

issing

-0.13

redient

-0.13

POSITIVE LOGITS

 action

0.19

 interest

0.18

 concern

0.17

uin

0.17

 focus

0.17

 greatest

0.16

 refuge

0.16

 study

0.16

operation

0.15

 enquiry

0.15

Activations Density 0.120%

phrases indicating areas, fields, or places of interest or focus

No Comments

No Known Activations