INDEX

Explanations

references to military actions and strategies

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

EMS

-0.17

 unrestricted

-0.15

 Noir

-0.13

steen

-0.13

 Bowie

-0.13

lick

-0.13

Dragging

-0.13

Î»Îµ

-0.13

Ã©rt

-0.13

ertz

-0.13

POSITIVE LOGITS

arget

0.16

target

0.15

.mit

0.15

HeaderCode

0.14

 targeting

0.14

_ctxt

0.14

aben

0.14

-target

0.14

frog

0.14

ÏĥÎ¹Î¿

0.14

Activations Density 0.042%

references to military actions and strategies

No Comments

No Known Activations