INDEX

Explanations

references to devices, platforms, and hardware specifications in the context of technology and compatibility

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

heimer

-0.17

artin

-0.16

ÑĢÑĥÐ±

-0.15

-ios

-0.15

arness

-0.15

avir

-0.15

atos

-0.15

ãĥ¼ãĤ¯

-0.15

áº£

-0.14

opy

-0.14

POSITIVE LOGITS

orsch

0.16

 equipped

0.14

å°º

0.14

ajo

0.13

ä»ĭ

0.13

 eskort

0.13

 gesch

0.13

!=(

0.13

 capable

0.13

 Narrow

0.13

Activations Density 0.083%

references to devices, platforms, and hardware specifications in the context of technology and compatibility

No Comments

No Known Activations