INDEX

Explanations

references to historical events and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ìĹĩ

-0.17

ullet

-0.15

 gods

-0.14

éĿ©åĳ½

-0.14

orgh

-0.14

hma

-0.14

onga

-0.14

illez

-0.14

 Ø§ÙĨÙĤÙĦ

-0.14

zyst

-0.14

POSITIVE LOGITS

 crus

0.36

 Crus

0.35

 Templ

0.34

 Hosp

0.28

pap

0.27

 knights

0.26

 Knights

0.26

 templ

0.26

 knight

0.24

templ

0.24

Activations Density 0.039%

references to historical events and figures

No Comments

No Known Activations