INDEX

Explanations

references to piracy, particularly in relation to media and cultural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

orig

-0.15

arked

-0.15

RI

-0.15

eya

-0.14

 Abel

-0.14

=center

-0.14

gam

-0.13

 barriers

-0.13

HA

-0.13

 capital

-0.13

POSITIVE LOGITS

ignet

0.17

Ð¾Ð·ÐµÐ¼

0.15

acker

0.15

arda

0.14

 Loose

0.14

eland

0.14

ulas

0.14

atures

0.14

istine

0.14

asso

0.14

Activations Density 0.014%

references to piracy, particularly in relation to media and cultural contexts

No Comments

No Known Activations