INDEX

Explanations

phrases that encourage visualization or imaginative thinking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

age

-0.19

tÃ©

-0.17

 latter

-0.16

oref

-0.16

istrovstvÃŃ

-0.16

iker

-0.16

way

-0.15

ponce

-0.15

isma

-0.14

romo

-0.14

POSITIVE LOGITS

ous

0.17

 scenarios

0.16

istic

0.15

 scenario

0.15

aukee

0.14

bras

0.14

lesi

0.14

ãģ¾ãģł

0.14

ERSIST

0.14

Activations Density 0.028%

phrases that encourage visualization or imaginative thinking

No Comments

No Known Activations

phrases that encourage visualization or imaginative thinking

No Comments

No Known Activations