INDEX

Explanations

strategic discussions and references related to defense and military capabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ruh

-0.15

[sizeof

-0.15

ippi

-0.15

ikel

-0.14

ä»²

-0.13

AXB

-0.13

ilden

-0.13

_cats

-0.13

´Ŀ

-0.13

å¥ı

-0.13

POSITIVE LOGITS

 defense

1.04

 defence

1.02

-defense

0.86

defense

0.84

 Defense

0.82

 defenses

0.82

 Defence

0.79

 defend

0.77

Defense

0.77

 defensive

0.71

Activations Density 0.256%

strategic discussions and references related to defense and military capabilities

No Comments

No Known Activations

strategic discussions and references related to defense and military capabilities

No Comments

No Known Activations