INDEX

Explanations

specific references to events or performance metrics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

esus

-0.16

ing

-0.15

inski

-0.14

 Abraham

-0.14

jour

-0.14

 Accounting

-0.13

ÑĢÐ°Ð±

-0.13

roker

-0.13

hiba

-0.13

Ð¸Ð½Ð³

-0.13

POSITIVE LOGITS

ude

0.17

otch

0.17

ike

0.15

amac

0.15

zzle

0.14

vec

0.14

ama

0.14

vecs

0.13

 caliente

0.13

Activations Density 0.536%

specific references to events or performance metrics in various contexts

No Comments

No Known Activations