INDEX

Explanations

names or terms related to geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ylko

-0.16

ÏĮÎ´

-0.16

taire

-0.16

ÑĩÐµÑģ

-0.16

airport

-0.15

 ÄĮesk

-0.15

ategy

-0.15

 Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»ÑĮ

-0.15

oise

-0.14

/Peak

-0.14

POSITIVE LOGITS

iner

0.18

ref

0.16

rel

0.14

 deline

0.14

nor

0.14

went

0.14

 positioning

0.14

idata

0.14

indr

0.14

ref

0.14

Activations Density 0.012%

names or terms related to geographical locations

No Comments

No Known Activations