INDEX

Explanations

references to organizations and initiatives related to security and strategy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

éĿ©åĳ½

-0.15

 Marketing

-0.15

Ð¾Ð²ÐµÑĢ

-0.14

Marketing

-0.14

erken

-0.14

eln

-0.14

posables

-0.14

_NOP

-0.14

ovie

-0.14

ATTR

-0.14

POSITIVE LOGITS

 policy

0.16

-policy

0.16

 Policy

0.16

.policy

0.15

policy

0.15

 political

0.15

forum

0.14

political

0.14

UNU

0.14

 intellectual

0.14

Activations Density 0.157%

references to organizations and initiatives related to security and strategy

No Comments

No Known Activations