INDEX

Explanations

location and directional information related to places

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

ibbon

-0.16

 Acts

-0.15

 ninh

-0.15

lok

-0.15

stadt

-0.14

Ð¾Ð³ÑĢÐ°Ð´

-0.14

çļĦäºĭ

-0.13

 evid

-0.13

ëª¨

-0.13

ä»®

-0.13

POSITIVE LOGITS

æ½®

0.16

uster

0.14

owell

0.14

anmar

0.13

Ø§Ø©

0.13

unted

0.13

BuilderFactory

0.13

 Olsen

0.13

PosX

0.13

.Xaml

0.13

Activations Density 0.112%

location and directional information related to places

No Comments

No Known Activations