INDEX

Explanations

references to legal terminology and procedural documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

$MESS

-0.18

 mastur

-0.14

Uvs

-0.13

GetCurrent

-0.13

;base

-0.13

 addCriterion

-0.12

/********************************************************************************

-0.12

 UIResponder

-0.12

POSITIVE LOGITS

 latter

0.16

ingu

0.13

.offsetTop

0.13

AndView

0.13

ÐµÐ·Ð¿ÐµÑĩ

0.12

(...)↵

0.12

 prere

0.11

ovit

0.11

esium

0.11

ãģļ

0.11

Activations Density 0.415%

references to legal terminology and procedural documentation

No Comments

No Known Activations