INDEX

Explanations

instances of the word "happen" and its variations, highlighting occurrences or events

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

achie

-0.18

udit

-0.17

usat

-0.16

à¤¤à¤®

-0.15

é©

-0.15

nev

-0.15

 Microsystems

-0.14

ÑĤÐ¸Ñı

-0.14

oger

-0.13

POSITIVE LOGITS

stance

0.23

STANCE

0.16

eyi

0.15

elize

0.15

oir

0.15

 mentioning

0.14

ally

0.14

Ã¶yle

0.14

ERRU

0.14

 coinc

0.14

Activations Density 0.013%

instances of the word "happen" and its variations, highlighting occurrences or events

No Comments

No Known Activations