INDEX

Explanations

sections marked with headings or titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ius

-0.16

 Fleming

-0.15

nan

-0.14

 MEMORY

-0.14

nen

-0.14

epad

-0.14

ls

-0.14

ulers

-0.13

 buggy

-0.13

 Thrones

-0.13

POSITIVE LOGITS

olley

0.19

uras

0.16

elic

0.15

ura

0.15

affle

0.15

 beyond

0.14

atin

0.14

PCA

0.14

 Typeface

0.14

clas

0.13

Activations Density 0.000%

sections marked with headings or titles

No Comments

No Known Activations