INDEX

Explanations

terms related to military hardware and weaponry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

alam

-0.16

oya

-0.16

ottie

-0.15

iesel

-0.15

ileo

-0.14

olet

-0.14

 Holmes

-0.13

 invert

-0.13

POSITIVE LOGITS

 mount

0.24

 trainable

0.23

 mounts

0.22

-mount

0.21

 twin

0.20

Gat

0.19

 magazines

0.19

 mounting

0.19

 Brow

0.18

_mount

0.18

Activations Density 0.010%

terms related to military hardware and weaponry

No Comments

No Known Activations