INDEX

Explanations

instances of the syllable "mo" or variations thereof in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

bor

-0.16

porate

-0.15

uj

-0.15

agen

-0.15

fel

-0.14

ÑĤÐ¾ÑĦ

-0.14

int

-0.14

 Sunder

-0.14

itesse

-0.14

POSITIVE LOGITS

mo

0.25

Mo

0.25

ieties

0.24

ambique

0.23

eller

0.23

oring

0.23

ody

0.23

zzarella

0.23

Mo

0.22

ODY

0.21

Activations Density 0.014%

instances of the syllable "mo" or variations thereof in different contexts

No Comments

No Known Activations