INDEX

Explanations

references to scientific publications or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Pres

-0.19

ocha

-0.17

Pres

-0.16

pres

-0.15

ipt

-0.15

æĸĹ

-0.15

erra

-0.14

ayer

-0.14

Cod

-0.14

ores

-0.14

POSITIVE LOGITS

slu

0.15

cling

0.15

-await

0.15

CLUD

0.14

ä¿®

0.14

reffen

0.14

AREST

0.14

eyn

0.14

ufe

0.14

onso

0.14

Activations Density 0.000%

references to scientific publications or citations

No Comments

No Known Activations