INDEX

Explanations

references to DIY activities and community engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

sez

-0.16

æ¡

-0.15

VERSE

-0.15

UserCode

-0.15

 therap

-0.14

rpt

-0.14

 thÃ¢n

-0.14

ieber

-0.14

ÑĥÐ²

-0.13

tdown

-0.13

POSITIVE LOGITS

exe

0.17

0.15

quette

0.15

rack

0.14

Bot

0.13

 governmental

0.13

FIG

0.13

Éµ

0.13

exion

0.13

Activations Density 0.011%

references to DIY activities and community engagement

No Comments

No Known Activations