INDEX

Explanations

specific numerical values or dates

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

#echo

-0.18

ollipop

-0.17

velt

-0.17

ÎŃÎ½

-0.17

fel

-0.17

 sefer

-0.16

 trá»įng

-0.16

swick

-0.15

gua

-0.15

exion

-0.14

POSITIVE LOGITS

occo

0.17

ervas

0.17

0.15

clus

0.14

xp

0.14

 GENERATED

0.13

Scaler

0.13

 scal

0.13

 dynam

0.13

Activations Density 0.022%

specific numerical values or dates

No Comments

No Known Activations