INDEX

Explanations

phrases that indicate familiarity or recognition of concepts, especially those that are labeled or categorized

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

xx

-0.16

iones

-0.14

gebn

-0.14

 ØªÙĪØ³

-0.14

Um

-0.14

 disb

-0.13

vÃŃ

-0.13

IMA

-0.13

 neur

-0.13

ARA

-0.13

POSITIVE LOGITS

witter

0.15

bij

0.15

dzi

0.14

oop

0.14

rase

0.14

rus

0.14

Ov

0.13

 sebagai

0.13

ableObject

0.13

 refer

0.13

Activations Density 0.023%

phrases that indicate familiarity or recognition of concepts, especially those that are labeled or categorized

No Comments

No Known Activations