INDEX

Explanations

hierarchical structures and levels within a content or process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rement

-0.16

eless

-0.15

iquer

-0.15

umbing

-0.15

Pg

-0.14

ìĹ´

-0.14

Å¡il

-0.14

vrd

-0.14

ogne

-0.14

zung

-0.14

POSITIVE LOGITS

una

0.16

matter

0.15

Ctl

0.14

IENCE

0.14

 Boyle

0.14

uno

0.14

iot

0.14

afen

0.14

BJ

0.13

Activations Density 0.100%

hierarchical structures and levels within a content or process

No Comments

No Known Activations