INDEX

Explanations

references to geographic locations and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Wolff

-0.16

aho

-0.16

ÐµÑĢÐ±

-0.14

Ð°Ð»Ñĭ

-0.14

Ãłng

-0.14

erview

-0.14

cente

-0.14

 soll

-0.14

Ã¼rn

-0.14

enda

-0.13

POSITIVE LOGITS

uspend

0.15

åĪĴ

0.14

 seins

0.14

 Hlav

0.13

 Wein

0.13

 Vine

0.13

rawer

0.13

omatic

0.13

emed

0.13

Activations Density 0.039%

references to geographic locations and regions

No Comments

No Known Activations