INDEX

Explanations

discussions related to survival and preparedness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

abad

-0.15

åĭĩ

-0.15

é¬¼

-0.14

lesai

-0.14

rvÃ©

-0.14

ç¸¾

-0.14

istrovstvÃŃ

-0.14

okable

-0.14

lea

-0.14

Ãªn

-0.13

POSITIVE LOGITS

 scenarios

0.20

 scenario

0.20

Scenario

0.19

 Scenario

0.17

lik

0.16

 Prepare

0.15

addon

0.15

 Preparation

0.15

scenario

0.15

 likely

0.15

Activations Density 0.285%

discussions related to survival and preparedness

No Comments

No Known Activations