INDEX

Explanations

references to academic disciplines or research classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iá»ĥm

-0.15

 varargin

-0.15

bara

-0.14

ÐµÑĢÐ²

-0.14

agu

-0.14

mvc

-0.13

eniz

-0.13

hari

-0.13

cken

-0.13

POSITIVE LOGITS

zens

0.17

 accordingly

0.15

ESA

0.15

pta

0.15

Lud

0.15

ofire

0.14

EB

0.14

 twice

0.14

ĩ

0.14

ardy

0.14

Activations Density 0.002%

references to academic disciplines or research classifications

No Comments

No Known Activations