INDEX

Explanations

phrases related to political controversies and actions taken against public figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

atsu

-0.15

iban

-0.15

nop

-0.14

bah

-0.14

ovi

-0.14

Vie

-0.13

èĦ

-0.13

Æł

-0.13

.namespace

-0.13

quip

-0.13

POSITIVE LOGITS

 Suff

0.16

 Hospitality

0.15

 Zahl

0.14

 Germ

0.14

alle

0.14

rc

0.13

 trÃŃ

0.13

 citiz

0.13

 suff

0.13

orna

0.13

Activations Density 0.204%

phrases related to political controversies and actions taken against public figures

No Comments

No Known Activations