INDEX

Explanations

phrases indicating conditions or contexts that are contingent upon specific situations or moments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 near

-0.17

Increment

-0.15

and

-0.15

 Niet

-0.15

ocker

-0.15

mina

-0.15

erman

-0.14

 Increment

-0.14

lib

-0.14

ritel

-0.14

POSITIVE LOGITS

este

0.16

ilik

0.16

lasses

0.16

IFY

0.15

iators

0.15

funcs

0.15

PTS

0.14

anke

0.14

 à¤®à¤¶

0.14

 Feinstein

0.14

Activations Density 0.046%

phrases indicating conditions or contexts that are contingent upon specific situations or moments

No Comments

No Known Activations