INDEX

Explanations

references to specific geographical locations and political contexts

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

iges

-0.17

htmlspecialchars

-0.15

oda

-0.15

ÐķÐ¡

-0.15

ulin

-0.15

.SC

-0.15

ä¸¸

-0.14

thinkable

-0.14

oux

-0.14

 ÑĩÐµÐ³Ð¾

-0.14

POSITIVE LOGITS

Khu

0.17

æ²ĸ

0.16

æ®Ĭ

0.15

oons

0.15

OMEM

0.15

asonry

0.14

.optim

0.14

ilar

0.14

Tal

0.14

Activations Density 0.053%

references to specific geographical locations and political contexts

No Comments

No Known Activations