INDEX

Explanations

mentions of prominent political figures or leaders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 gyro

-0.15

ijo

-0.15

ISOString

-0.14

nell

-0.14

usu

-0.14

 Chall

-0.14

.tencent

-0.13

/perl

-0.13

pii

-0.13

/Instruction

-0.13

POSITIVE LOGITS

onda

0.17

issor

0.16

ãĥ³ãĥĦ

0.14

calar

0.13

ovat

0.13

 Ð´Ð¾Ñģ

0.13

ocr

0.13

Ð½Ð¾ÑĪ

0.13

onta

0.13

Activations Density 0.169%

mentions of prominent political figures or leaders

No Comments

No Known Activations