INDEX

Explanations

references to the word "fort" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ikan

-0.16

PECT

-0.15

perator

-0.15

å±Ģ

-0.15

aterno

-0.15

bsub

-0.15

ÅĤu

-0.15

iyah

-0.15

æļĸ

-0.14

æĹ

-0.14

POSITIVE LOGITS

aleza

0.31

una

0.31

unes

0.30

resses

0.30

ress

0.30

uit

0.29

une

0.29

ifications

0.29

itude

0.28

ification

0.26

Activations Density 0.011%

references to the word "fort" and its variations

No Comments

No Known Activations