INDEX

Explanations

references to military experiments and their outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Erot

-0.15

 MetroFramework

-0.14

odash

-0.14

 Toilet

-0.14

 táº¯c

-0.14

ãģĵãĤĵãģ«

-0.14

å°¿

-0.14

sem

-0.13

parsed

-0.13

erset

-0.13

POSITIVE LOGITS

 experiments

0.32

 experimental

0.29

 experiment

0.28

 Experiment

0.27

 genetic

0.27

experiment

0.26

 Experimental

0.25

å®ŀéªĮ

0.25

 research

0.25

experimental

0.24

Activations Density 0.177%

references to military experiments and their outcomes

No Comments

No Known Activations