INDEX

Explanations

technical descriptions related to visual representations or diagrams in documentation

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

folk

-0.15

uard

-0.14

ylon

-0.14

 Valle

-0.14

 overs

-0.14

 Enum

-0.14

 Copp

-0.14

anus

-0.14

ystone

-0.14

elper

-0.14

POSITIVE LOGITS

iÅ¡

0.18

incinn

0.15

isman

0.15

ERICA

0.14

]={↵

0.14

iska

0.14

.Timer

0.14

ramids

0.14

iben

0.14

utow

0.13

Activations Density 0.031%

technical descriptions related to visual representations or diagrams in documentation

No Comments

No Known Activations