INDEX

Explanations

references to specific characters and elements from Arthurian legend

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

mitt

-0.17

 PureComponent

-0.16

MBED

-0.15

ctp

-0.15

ieg

-0.15

ARRANT

-0.15

oran

-0.14

Sele

-0.14

htag

-0.14

bett

-0.13

POSITIVE LOGITS

inery

0.15

viso

0.15

 McCoy

0.14

/owl

0.14

lector

0.14

 cÃ©lib

0.14

bserv

0.14

0.13

 Bend

0.13

 fitted

0.13

Activations Density 0.001%

references to specific characters and elements from Arthurian legend

No Comments

No Known Activations