INDEX

Explanations

references to specific time periods or historical dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oster

-0.19

ois

-0.16

ao

-0.16

bang

-0.15

sts

-0.14

itoris

-0.14

 Vital

-0.14

ansi

-0.14

 Karn

-0.14

echa

-0.14

POSITIVE LOGITS

ifax

0.17

izi

0.15

elig

0.15

 Nack

0.15

agu

0.15

åį·

0.14

 Trilogy

0.14

urm

0.14

ierre

0.14

elow

0.14

Activations Density 0.200%

references to specific time periods or historical dates

No Comments

No Known Activations