INDEX

Explanations

references to various versions and comparisons of products or technologies, particularly in the context of software and automobiles

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

uada

-0.16

ativ

-0.15

ilip

-0.15

azer

-0.14

okus

-0.14

mada

-0.14

ç«ĭãģ¦

-0.14

 pitch

-0.14

Zar

-0.13

alone

-0.13

POSITIVE LOGITS

 except

0.16

çĽ¸åĲĮ

0.16

Except

0.15

goo

0.15

sov

0.15

Crud

0.15

scr

0.14

ritel

0.14

pong

0.14

inders

0.14

Activations Density 0.096%

references to various versions and comparisons of products or technologies, particularly in the context of software and automobiles

No Comments

No Known Activations