INDEX

Explanations

references to actions and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oe

-0.16

 Gest

-0.14

reuse

-0.14

arra

-0.14

ams

-0.14

ãĥĶãĥ¼

-0.13

ä»Ģ

-0.13

IDD

-0.13

ond

-0.13

ItemSelected

-0.13

POSITIVE LOGITS

aterangepicker

0.17

athers

0.16

hart

0.16

AppBundle

0.15

FI

0.15

 shall

0.15

dds

0.14

enger

0.14

ÑĩÐ¸Ð¼

0.14

tan

0.14

Activations Density 0.131%

references to actions and decision-making processes

No Comments

No Known Activations