INDEX

Explanations

aspects related to objects and actions in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

\CMS

-0.17

raquo

-0.17

-eslint

-0.16

odore

-0.14

ervlet

-0.14

TransparentColor

-0.14

'gc

-0.13

inki

-0.13

isman

-0.13

_softc

-0.13

POSITIVE LOGITS

“

0.12

elan

0.12

"class

0.12

ADV

0.12

 squat

0.12

âĢ¦

0.11

“

0.11

ï¼ģ↵↵

0.11

Activations Density 0.003%

aspects related to objects and actions in descriptions

No Comments

No Known Activations