INDEX

Explanations

phrases indicating certainty or definiteness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-0.16

Convention

-0.15

 Convention

-0.14

Ð¾Ñı

-0.14

irs

-0.14

agem

-0.14

ìļĶ

-0.14

æĲº

-0.13

Éµ

-0.13

POSITIVE LOGITS

strup

0.16

="{!!

0.16

Erg

0.16

hod

0.15

rance

0.15

 ç¤

0.15

tin

0.14

 arithmetic

0.14

 gain

0.14

rit

0.14

Activations Density 0.000%

phrases indicating certainty or definiteness

No Comments

No Known Activations