INDEX

Explanations

names of individuals or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÑģÑĮ

-0.20

jac

-0.19

jt

-0.18

 otherwise

-0.17

ke

-0.17

verage

-0.17

jang

-0.17

jes

-0.17

jad

-0.17

jk

-0.17

POSITIVE LOGITS

er

0.20

ing

0.18

ume

0.17

ding

0.17

ledge

0.17

oci

0.16

 EntryPoint

0.15

ness

0.15

erb

0.15

ful

0.15

Activations Density 0.097%

names of individuals or characters

No Comments

No Known Activations