INDEX

Explanations

occurrences of the word "speaks" or 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

baugh

-0.16

Ã¤Ã¤n

-0.15

ourn

-0.15

ouz

-0.14

ogui

-0.14

ÃŃna

-0.14

ouri

-0.14

rosso

-0.14

 Everyday

-0.14

unan

-0.14

POSITIVE LOGITS

zial

0.27

ake

0.27

aks

0.26

akers

0.25

acial

0.25

arm

0.24

ical

0.24

icher

0.24

ck

0.23

aking

0.23

Activations Density 0.007%

occurrences of the word "speaks" or its variations

No Comments

No Known Activations