INDEX

Explanations

references to comparisons or contrasts in a variety of contexts

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

ModelProperty

-0.15

andler

-0.15

Kum

-0.14

rese

-0.14

eq

-0.14

 Stephan

-0.14

 Maul

-0.13

mur

-0.13

emann

-0.13

POSITIVE LOGITS

pes

0.16

 prim

0.16

rch

0.15

 Prim

0.15

uds

0.14

zbek

0.14

mlink

0.13

he

0.13

.Permission

0.13

 ÙģÙĤ

0.13

Activations Density 0.193%

references to comparisons or contrasts in a variety of contexts

No Comments

No Known Activations