INDEX

Explanations

references to numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

avl

-0.17

 MÄĽst

-0.15

asl

-0.15

ONG

-0.15

oku

-0.15

 çĿ

-0.14

uml

-0.14

InputDialog

-0.14

idon

-0.14

inces

-0.13

POSITIVE LOGITS

uez

0.16

owie

0.16

grim

0.15

uelles

0.15

antan

0.14

rome

0.14

 carn

0.14

 Sand

0.13

Activations Density 0.169%

references to numerical data or statistics

No Comments

No Known Activations