INDEX

Explanations

references to land or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oter

-0.18

acs

-0.17

çİĩ

-0.16

olet

-0.16

ipient

-0.15

 Mull

-0.15

ansi

-0.15

abilit

-0.15

ç¢¼

-0.15

èıĮ

-0.15

POSITIVE LOGITS

locked

0.24

ingham

0.21

owners

0.19

owner

0.19

fills

0.19

idl

0.18

lady

0.17

lords

0.17

OLT

0.17

lord

0.17

Activations Density 0.018%

references to land or locations

No Comments

No Known Activations