INDEX

Explanations

terms related to complaints and grievances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ucken

-0.17

antaged

-0.16

ÑĪÑĤÐ¾Ð²

-0.15

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

-0.15

assic

-0.14

achs

-0.14

presso

-0.14

uarios

-0.14

 Parsons

-0.14

fieldname

-0.14

POSITIVE LOGITS

enance

0.21

pects

0.18

iance

0.16

à¸Ĭà¸Ńà¸ļ

0.15

slaught

0.15

inerary

0.14

itude

0.14

HIP

0.14

åĦ¿

0.14

olation

0.14

Activations Density 0.253%

terms related to complaints and grievances

No Comments

No Known Activations