INDEX

Explanations

instances of the word "start" and its variations in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rint

-0.17

usu

-0.16

au

-0.15

rf

-0.15

iston

-0.14

sey

-0.14

/Area

-0.14

 airst

-0.14

mtree

-0.14

anders

-0.14

POSITIVE LOGITS

tir

0.18

swith

0.17

ling

0.15

yr

0.15

 Disclaimer

0.15

vice

0.15

VICE

0.15

ecz

0.15

ellite

0.14

Activations Density 0.094%

instances of the word "start" and its variations in various forms

No Comments

No Known Activations