INDEX

Explanations

geographical locations or state abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Patt

-0.16

ozor

-0.15

feit

-0.15

 ÑģÐ¾Ð±Ð¾Ð¹

-0.15

-t

-0.14

ille

-0.14

bilt

-0.14

 trap

-0.14

gence

-0.14

athon

-0.14

POSITIVE LOGITS

Ð½Ð°ÑĤ

0.16

achten

0.15

 tÃ´

0.14

ÑįÑĤÐ¾Ð¼Ñĥ

0.14

KeySpec

0.14

ensely

0.14

owell

0.13

 ÑĢÐµÐ±

0.13

_timezone

0.13

amo

0.13

Activations Density 0.056%

geographical locations or state abbreviations

No Comments

No Known Activations