INDEX

Explanations

terms related to technical specifications and performance metrics

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

Sharper

-0.14

ean

-0.14

lisi

-0.14

gart

-0.14

mana

-0.13

aign

-0.13

itag

-0.13

phants

-0.13

 autoc

-0.13

@include

-0.13

POSITIVE LOGITS

ippo

0.16

ubb

0.15

ippi

0.15

alie

0.14

nej

0.14

Ð±Ð¾ÑĢ

0.14

å¥ı

0.14

 Weld

0.14

Mag

0.14

Activations Density 0.117%

terms related to technical specifications and performance metrics

No Comments

No Known Activations