INDEX

Explanations

relationships and dynamics between individuals, particularly highlighting conflict and emotional interplay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

allis

-0.16

errar

-0.16

ibo

-0.16

irez

-0.15

deniz

-0.15

 Keystone

-0.15

voke

-0.14

oogle

-0.14

 Sachs

-0.14

ilogue

-0.14

POSITIVE LOGITS

 whom

0.15

roat

0.15

inges

0.14

è®¸

0.14

Pik

0.13

WIN

0.13

 fellow

0.13

esse

0.13

apt

0.13

Activations Density 0.323%

relationships and dynamics between individuals, particularly highlighting conflict and emotional interplay

No Comments

No Known Activations