INDEX

Explanations

components related to data manipulation and structure management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SSI

-0.16

ulares

-0.16

esser

-0.16

Ã¡zi

-0.15

AGER

-0.15

elez

-0.15

ocos

-0.14

utut

-0.14

uci

-0.14

aeper

-0.14

POSITIVE LOGITS

0.16

 Conc

0.15

izia

0.15

oid

0.15

ling

0.15

chy

0.14

ost

0.14

BAB

0.14

 æŀ

0.13

Activations Density 0.592%

components related to data manipulation and structure management

No Comments

No Known Activations