INDEX

Explanations

phrases and expressions indicating association or connection, particularly focusing on relationships among people or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÏĩÎ·

-0.16

ishment

-0.15

istr

-0.14

Ø®Ø°

-0.13

esser

-0.13

bject

-0.13

odoxy

-0.13

LOAT

-0.13

Ã©rt

-0.13

 exponent

-0.13

POSITIVE LOGITS

 connections

0.25

 ties

0.22

 experience

0.21

 interests

0.20

 ambitions

0.19

 skills

0.19

 access

0.19

connections

0.19

 aspirations

0.18

 wings

0.18

Activations Density 0.330%

phrases and expressions indicating association or connection, particularly focusing on relationships among people or concepts

No Comments

No Known Activations