INDEX

Explanations

phrases indicating expectations or occurrences of events in the future

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.18

ieg

-0.15

lek

-0.14

illance

-0.14

esch

-0.14

á»¥y

-0.14

 intric

-0.14

exp

-0.14

POSITIVE LOGITS

avn

0.17

å¦

0.17

Extern

0.15

amsung

0.15

ÙĬÙĥØ§

0.14

alker

0.14

åŀ

0.14

WithOptions

0.14

 Monter

0.14

TOTYPE

0.14

Activations Density 0.217%

phrases indicating expectations or occurrences of events in the future

No Comments

No Known Activations