INDEX

Explanations

structural coherence and thematic unity in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

DataTask

-0.14

Ã¹y

-0.14

iane

-0.13

æ¢¨

-0.13

 resilience

-0.13

vang

-0.13

UTH

-0.13

-sizing

-0.13

iano

-0.13

Opens

-0.13

POSITIVE LOGITS

 coherence

0.30

 coherent

0.30

 consistency

0.26

 unity

0.25

 continuity

0.24

è¿ŀ

0.23

coh

0.22

 cohesive

0.22

 unified

0.22

 consistent

0.22

Activations Density 0.250%

structural coherence and thematic unity in writing

No Comments

No Known Activations