INDEX

Explanations

mentions of car features and specifications

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

Ð±Ð¾ÑĤ

-0.17

 Administr

-0.15

 attachments

-0.15

 Attach

-0.14

 attachment

-0.14

alan

-0.14

 Outer

-0.14

igger

-0.14

 Staff

-0.14

ome

-0.14

POSITIVE LOGITS

 dashboard

0.24

 dash

0.24

 Dashboard

0.22

Dash

0.20

Dashboard

0.20

_dash

0.19

 dashes

0.19

dashboard

0.19

 Dash

0.19

 Ø¯Ø§Ø´

0.18

Activations Density 0.083%

mentions of car features and specifications

No Comments

No Known Activations