INDEX

Explanations

references to sections or citations in academic papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

.dds

-0.16

åĩ½

-0.15

.scalablytyped

-0.15

à¤¾à¤°à¤ķ

-0.15

ÐºÐ¾

-0.14

 NSLocalizedString

-0.14

LocalizedString

-0.14

Sez

-0.14

xcd

-0.14

ë°ľ

-0.14

POSITIVE LOGITS

oller

0.17

ogany

0.16

Im

0.15

.mk

0.15

eyer

0.15

acen

0.14

nesc

0.14

 overlay

0.14

ÐµÑĢÐ³

0.14

exp

0.13

Activations Density 0.030%

references to sections or citations in academic papers

No Comments

No Known Activations