INDEX

Explanations

terms related to comparison and differentiation

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

assi

-0.15

 versa

-0.15

ActivityIndicator

-0.14

RIES

-0.14

 Alam

-0.14

ÎºÏħ

-0.14

essler

-0.13

 trotz

-0.13

acks

-0.13

urger

-0.13

POSITIVE LOGITS

Si

0.21

Si

0.19

 stock

0.19

si

0.18

stock

0.18

appl

0.17

Ã´n

0.16

si

0.16

æŀ

0.16

 parc

0.16

Activations Density 0.007%

terms related to comparison and differentiation

No Comments

No Known Activations