INDEX

Explanations

references to prominent individuals or groups within a social or political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

iti

-0.16

ÑĥÐ»Ñİ

-0.16

ufen

-0.16

illos

-0.16

Ð°Ð»ÐµÐ¶

-0.16

erli

-0.15

andle

-0.15

icas

-0.14

ÐµÐ½ÑĤÐ¸

-0.14

chÃ¡z

-0.14

POSITIVE LOGITS

 Anonymous

0.15

 junto

0.14

ä¸Ģèµ·

0.14

å±ĭ

0.14

reen

0.14

UNET

0.13

inx

0.13

 ÑħÑĤÐ¾

0.13

orus

0.13

.anchor

0.13

Activations Density 0.051%

references to prominent individuals or groups within a social or political context

No Comments

No Known Activations

references to prominent individuals or groups within a social or political context

No Comments

No Known Activations