INDEX

Explanations

proper nouns related to fictional characters and locations, particularly in animated media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.16

RITE

-0.16

dialogs

-0.14

mts

-0.14

DataMember

-0.14

 impro

-0.13

 Drum

-0.13

ental

-0.13

 Liver

-0.13

POSITIVE LOGITS

andas

0.17

UNU

0.15

esel

0.14

_UNSIGNED

0.14

avad

0.14

ADOR

0.14

åŃĹ

0.13

ÎºÏĮ

0.13

ingham

0.13

ÃŃv

0.13

Activations Density 0.125%

proper nouns related to fictional characters and locations, particularly in animated media

No Comments

No Known Activations