INDEX

Explanations

specific technical or scientific terms related to components and structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

kus

-0.17

enko

-0.16

gon

-0.16

uien

-0.15

uer

-0.15

ãĥ©ãĥ¼

-0.15

ierung

-0.14

ANCH

-0.14

ittel

-0.14

vio

-0.14

POSITIVE LOGITS

ed

0.18

Tar

0.15

abeth

0.14

 runoff

0.14

 shoots

0.14

ensus

0.13

sworth

0.13

 taraf

0.13

 desk

0.13

unting

0.13

Activations Density 0.212%

specific technical or scientific terms related to components and structures

No Comments

No Known Activations