INDEX

Explanations

specific structural details related to titles, categories, and other identifiers in various contexts such as films, profiles, and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ahan

-0.15

amar

-0.15

ummer

-0.15

ridor

-0.14

æĥ

-0.14

aret

-0.14

ÑĪÐ°

-0.14

zar

-0.14

aub

-0.14

iked

-0.14

POSITIVE LOGITS

(s

0.19

ë§ŀ

0.14

 scre

0.14

0.13

å±±å¸Ĥ

0.13

MAS

0.13

iface

0.13

 Riverside

0.13

Activations Density 0.102%

specific structural details related to titles, categories, and other identifiers in various contexts such as films, profiles, and products

No Comments

No Known Activations